AIndex
Kostenlos laden

Compare Sourcegraph

Do not sell “better code search”. Sell agent cost control with proof.

Sourcegraph is strong at enterprise code search, code graph, Deep Search, Batch Changes, Insights and controls. AiIndexer should cover the indispensable workflows and win on local-first setup, simple pricing, agent packs and automatic ROI proof.

Generate pilot proofView feature registry
Generic search platform$16K+ buying anxiety

Broad platform value, longer rollout, harder proof for agent-token waste.

Agent context optimizer10k not 200k

Budgeted packs, cache-aware ordering, local controls and ROI reports on real code.

Runtime feature proof

Feature discovery is backed by metadata-only runtime evidence.

Public pages default to preview data. When a local SQLite, JSON or cloud summary is explicitly allowed, the same registry shows which workflows have been observed without exposing raw source.

0/26observed workflowsDemo preview, not runtime observed
0evidence item(s)no raw source included
26registered workflowsFeature Registry feeds web, CLI, MCP, dashboard, setup and VSCode.
4status fieldsEnabled, available, observed and buyer grade stay separate on public pages.

Feature visibility checklist

Sourcegraph comparison coverage, without overclaim.

Every feature named in the plan is mapped to an AiIndexer workflow, with availability and buyer grade shown before any parity claim.

Agent Cost AutopilotBeta

Agent Cost Autopilot

Budgeted plan before the agent starts reading.

Surface
CLI, MCP context, dashboard, pilot report
Buyer-safe status
Beta · Pilot-grade
Runtime
preview only
Context PacksBeta

Context Packs

Graph-ranked task packs with hashes, cache classes and exact anchors.

Surface
CLI pack, MCP links, PR Pack, dashboard timeline
Buyer-safe status
Beta · Pilot-grade
Runtime
preview only
Cache-Aware ContextFoundation

Cache-Aware Context

Stable and volatile context are separated so cache behavior is visible.

Surface
Autopilot, benchmarks, ROI dashboard, pilot report
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Proof / ROI DashboardBeta

Proof / ROI Dashboard

Tokens avoided, cost saved, time saved and predicted vs observed proof.

Surface
Dashboard, Pilot PDF, pricing, procurement export
Buyer-safe status
Beta · Pilot-grade
Runtime
preview only
Loop KillerFoundation

Agent Loop Killer

Repeated reads, ignored packs and loop recovery actions are surfaced.

Surface
CLI waste, dashboard waste table, MCP status, monitors
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Adoption DetectorFoundation

Agent Adoption Detector

Configured agents are checked against recent MCP usage.

Surface
Setup success, dashboard alerts, IDE sidebar, pilot report
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Deep SearchFoundation

Deep Search

Budgeted multi-step research returns citations and a stop condition.

Surface
CLI deep-search, MCP context, saved queries, dashboard evidence
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Sourcegraph parityFoundation

Sourcegraph Parity Layer

Parity language is explicit while Sourcegraph-class claims stay gated.

Surface
Compare Sourcegraph, pricing, pilot report, benchmarks
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Team Shared IndexFoundation

Team Shared Index

One commit-addressed team index with freshness and local fallback.

Surface
Team index status, dashboard, CI, MCP status
Buyer-safe status
Foundation · Foundation
Runtime
preview only
PR Context PackFoundation

PR Context Pack

Changed files, blast radius, tests, owners and risk gate are packaged.

Surface
CI artifact, dashboard PR packs, GitHub/GitLab comment
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Governed ContextFoundation

Governed Context

RBAC, redaction, denied paths and audit exports stay visible.

Surface
Governance audit, Enterprise policy, monitors, pilot report
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Pilot ReportFoundation

Pilot Report

Buyer-ready report with baseline, examples, risks and rollout tier.

Surface
CLI pilot, PDF export, dashboard, compare pages, pricing
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Batch AutopilotFoundation

Batch Autopilot

Dry-run migration plan with rollout gate before PR creation.

Surface
CLI batch-autopilot, dashboard batch runs, owners, PR metadata
Buyer-safe status
Foundation · Foundation
Runtime
preview only
InsightsFoundation

Insights & Monitoring

Saved query snapshots become trends instead of one-off searches.

Surface
Dashboard insights, saved queries, pilot report
Buyer-safe status
Foundation · Foundation
Runtime
preview only
MonitoringFoundation

Insights & Monitoring

Pattern alerts and threshold checks are explicit product surfaces.

Surface
Monitors, CI output, webhooks, governance alerts
Buyer-safe status
Foundation · Foundation
Runtime
preview only
OwnershipFoundation

Ownership & Blast Radius

Likely owners and affected tests are attached to risky changes.

Surface
PR Pack, Batch Autopilot, dashboard, IDE current diff
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Feature DiscoveryFoundation

VS Code, CLI and MCP Surfaces

No workflow ships as a hidden command or undocumented MCP action.

Surface
Feature registry, setup success, dashboard, docs, pricing
Buyer-safe status
Foundation · Foundation
Runtime
preview only
VSCodeFoundation

VS Code, CLI and MCP Surfaces

IDE actions mirror the same registry used by CLI, MCP and web.

Surface
VS Code sidebar and command palette
Buyer-safe status
Foundation · Foundation
Runtime
preview only
CLIFoundation

VS Code, CLI and MCP Surfaces

Commands expose the same feature names, statuses and JSON contracts.

Surface
aindex features, status, context, pack and workflow commands
Buyer-safe status
Foundation · Foundation
Runtime
preview only
MCPFoundation

VS Code, CLI and MCP Surfaces

Five tools route advanced actions without schema bloat.

Surface
context, search, navigate, status and remember
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Advanced Code NavigationFoundation

Advanced Code Navigation

architecture, dead-code, smells, audit, duplicates, implementations, type-hierarchy, map and rules are one router.

Surface
MCP navigate, CLI, docs, dashboard, architecture overview
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Cross-Session MemoryFoundation

Cross-Session Memory

Observations and run outcomes persist and are recalled across sessions, stored locally.

Surface
MCP remember, CLI, docs, dashboard, agent sessions
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Batch Search ToolsFoundation

Batch Search Tools

search action=batch groups related queries under one budget to cut round-trips.

Surface
MCP search, CLI, docs, dashboard, saved queries
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Self-Hosted & Air-GappedFoundation

Self-Hosted & Air-Gapped

Local SQLite index, no-network mode and metadata-only exports prove zero egress.

Surface
Security, Enterprise policy, CLI doctor, docs, dashboard
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Code Graph ExportFoundation

Code Graph Export

SCIP/LSIF interop and native full-fidelity .aig export/import keep the graph portable.

Surface
CLI scip, CLI graph, docs, dashboard, interop
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Auto-WikiFoundation

Auto-Wiki

A deterministic, metadata-only code wiki is rendered from the live graph with signatures and flows but no raw source.

Surface
CLI wiki, MCP navigate, docs, dashboard, architecture overview
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Change CouplingFoundation

Change Coupling

Git co-change pairs surface coupled neighbors a static dependency graph misses.

Surface
CLI context, MCP context, docs, dashboard, PR Pack
Buyer-safe status
Foundation · Foundation
Runtime
preview only
One-Call Context PipelineFoundation

One-Call Context Pipeline

One context call returns capsule, impact, memory recall and change-coupling together.

Surface
CLI context, MCP context, docs, dashboard, agent sessions
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Enterprise Access ControlFoundation

Enterprise Access Control

RBAC, SSO and SCIM are Enterprise entitlements enforced through governance policy.

Surface
Enterprise policy, governance audit, security, pricing, docs
Buyer-safe status
Foundation · Foundation
Runtime
preview only
Codebase AtlasFoundation

Codebase Atlas

A deterministic, metadata-only system model, drift report and ranked risk board for any AI-built repo.

Surface
CLI understand, MCP status, Studio Atlas home, dogfood page, docs
Buyer-safe status
Foundation · Foundation
Runtime
preview only

Buyer surfaces

Billing, security, benchmarks and pricing have explicit guardrails.

These surfaces support the feature story without turning foundations into shipped enterprise claims.

Feature registryLive

Every master-plan workflow is named, linked, tiered and tied to runtime feature proof.

The registry is generated from the same source used by pricing, dashboard, setup and MCP status.

Open surface
ROI DashboardFoundation

Autopilot runs, PR packs, team index freshness, adoption, waste, insights, monitors and governance are visible as one command center.

Demo preview and observed data stay clearly separated, with metadata-only runtime evidence.

Open surface
PricingLive

Plan tiers map to named workflows with runtime observed/available kept separate.

No plan page should imply Sourcegraph-class parity for foundation workflows.

Open surface
BillingFoundation

Checkout and portal paths are visible, with readiness gates and support fallback.

Billing is presented as guarded until live-sales readiness confirms checkout.

Open surface
SecurityFoundation

Local-first source posture, redaction, audit and Governed Context are connected.

Security copy stays metadata-only and avoids claiming hosted source indexing.

Open surface
BenchmarksLive

Public benchmark data is tied back to cache-aware context and pilot proof.

Benchmark pages distinguish measured local runs from positioning claims.

Open surface
Compare SourcegraphFoundation

Search, graph, Deep Search, Batch, Insights, Monitoring, Ownership, governance and ROI are mapped to registry-backed workflows.

The page names parity expectations while keeping Sourcegraph-class claims gated by availability and runtime evidence.

Open surface
Compare Cursor/CodyFoundation

AiIndexer is presented as the neutral MCP context layer under Cursor, Cody and other assistants.

The comparison avoids replacing IDE assistants; it focuses on shared packs, adoption checks, governance and ROI proof.

Open surface
Pilot reportFoundation

Autopilot, packs, adoption, governed context, team index, Sourcegraph parity and pricing recommendations become one buyer artifact.

Observed pilot inputs stay metadata-only, with demo preview clearly separated from real report data.

Open surface

Buyer-safe parity

Buyer-facing parity must separate shipped workflows from pilot foundations.

AiIndexer should be aggressive on the wedge, but precise on availability: live workflows are runnable, beta workflows are pilot-ready, foundation workflows are visible proof paths, and preview workflows are not sold as Sourcegraph-class.

ProBetapreview only

Agent Cost Autopilot

Pilot-grade · Buyer-safe for pilots, but still below fully hardened Sourcegraph-class parity.

Usable for pilots, with contracts still being hardened from observed runs.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nocontext action=autopilot
ProBetapreview only

Context Packs

Pilot-grade · Buyer-safe for pilots, but still below fully hardened Sourcegraph-class parity.

Usable for pilots, with contracts still being hardened from observed runs.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nocontext action=pack
ProFoundationpreview only

Cache-Aware Context

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nocontext action=cache
TeamBetapreview only

Proof / ROI Dashboard

Pilot-grade · Buyer-safe for pilots, but still below fully hardened Sourcegraph-class parity.

Usable for pilots, with contracts still being hardened from observed runs.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nostatus detail=roi
ProFoundationpreview only

Agent Loop Killer

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nostatus detail=waste
ProFoundationpreview only

Agent Adoption Detector

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nostatus detail=adoption
TeamFoundationpreview only

Team Shared Index

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nostatus detail=team-index
TeamFoundationpreview only

PR Context Pack

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nocontext action=pr-pack
EnterpriseFoundationpreview only

Governed Context

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nostatus detail=governance
TeamFoundationpreview only

Pilot Report

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nostatus detail=pilot
ProFoundationpreview only

Deep Search

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nocontext action=deep-search
TeamFoundationpreview only

Batch Autopilot

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nosearch action=batch
TeamFoundationpreview only

Insights & Monitoring

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nostatus detail=watches
TeamFoundationpreview only

Ownership & Blast Radius

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nonavigate action=blast-radius
TeamFoundationpreview only

Sourcegraph Parity Layer

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nostatus detail=features
FreeFoundationpreview only

VS Code, CLI and MCP Surfaces

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nostatus detail=features
ProFoundationpreview only

Advanced Code Navigation

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nonavigate action=architecture
ProFoundationpreview only

Cross-Session Memory

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: noremember action=search
ProFoundationpreview only

Batch Search Tools

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nosearch action=batch
EnterpriseFoundationpreview only

Self-Hosted & Air-Gapped

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nostatus detail=full
FreeFoundationpreview only

Code Graph Export

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nostatus detail=features
ProFoundationpreview only

Auto-Wiki

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nonavigate action=map
ProFoundationpreview only

Change Coupling

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nocontext action=autopilot
ProFoundationpreview only

One-Call Context Pipeline

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nocontext task="fix the checkout bug"
EnterpriseFoundationpreview only

Enterprise Access Control

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nostatus detail=governance
ProFoundationpreview only

Codebase Atlas

Foundation · Names the parity workflow and proof path without claiming full Sourcegraph-class depth.

Visible as a product workflow and pilot proof target; do not treat as fully shipped enterprise automation yet.

Metadata-only runtime evidence; no raw source included.

Enabled: yes · Available: yes · Observed: nostatus detail=atlas

How AiIndexer wins the pilot

The first install must end with proof, not another empty search box.

The wedge against a broad code intelligence platform is fast adoption plus a report that shows real agent waste, team index value and governance readiness.

Pilot action

Run Autopilot

Shows naive tokens, optimal pack, risks, tests and do-not-read paths.

aindex autopilot "fix billing login bug" --json

MCP: context action=autopilot task="fix billing login bug"
Pilot action

Generate PR Pack

Turns review into files touched, blast radius, owners, tests, risks and publish-safe comment metadata.

aindex pr-pack --pr 42 --repo owner/name --provider github --publish-comment --dry-run --json

MCP: context action=pr-pack pr=42 repo=owner/name
Pilot action

Check Adoption

Confirms each agent is configured and actually calling MCP.

aindex adoption --repair --json

MCP: status detail=adoption
Pilot action

Run Pilot Report

Creates JSON/PDF management proof with provenance, no raw source, savings, adoption, risk and recommendations.

aindex pilot --repos web api billing --pdf --json --output aindex-pilot-report.pdf --json-output pilot-report.json

MCP: status detail=pilot
Pilot action

Open ROI Dashboard

Displays observed savings, waste findings, team index state and governance audit.

aindex roi --json

MCP: status detail=roi

Non-negotiable product axes

Every release must make adoption, control, proof or parity stronger.

The product promise is not another search UI. It is a local/self-hosted context optimizer that makes agent work cheaper, faster, governed and provable.

5 minAdoptionSetup must end with Autopilot, PR Pack, Adoption Check, Pilot Report and ROI Dashboard.
local-firstControlNo raw source goes to cloud by default; self-hosted and air-gapped paths stay visible.
before/afterProofEvery workflow should tie back to tokens avoided, time saved, loops killed or risk reduced.
agent-firstParityCover search, graph, Deep Search, Batch, Insights, Monitoring, Ownership and audit.

Where AiIndexer must be credible

Parity earns the comparison. Agent ROI wins the deal.

The platform has to name the enterprise boxes buyers expect, while making the differentiator impossible to miss: budgeted context and proof on real agent runs.

LayerWhat must be presentWhy it matters
Code intelligence baselineSearch, symbols, references, callers, callees, multi-repo and saved queries.Needed so buyers trust the context graph.
Agent cost layerAutopilot, packs, cache-aware ordering, waste detection and predicted vs observed ROI.This is the AiIndexer wedge Sourcegraph does not lead with.
Team workflowsTeam Shared Index, PR Context Packs, Batch Autopilot, Ownership and monitors.This moves the product from solo CLI to team platform.
Enterprise controlsGoverned Context, path filters, redaction, audit logs and self-hosted deployment.This is what CTO/CISO buyers require before agent context can scale.
Adoption and proof loopSetup success, repair commands, pilot reports, dashboard proof and PDF export.This turns a technical install into a buying process buyers can repeat internally.
Code intelligence baselineMust be presentSearch, symbols, references, callers, callees, multi-repo and saved queries.WhyNeeded so buyers trust the context graph.
Agent cost layerMust be presentAutopilot, packs, cache-aware ordering, waste detection and predicted vs observed ROI.WhyThis is the AiIndexer wedge Sourcegraph does not lead with.
Team workflowsMust be presentTeam Shared Index, PR Context Packs, Batch Autopilot, Ownership and monitors.WhyThis moves the product from solo CLI to team platform.
Enterprise controlsMust be presentGoverned Context, path filters, redaction, audit logs and self-hosted deployment.WhyThis is what CTO/CISO buyers require before agent context can scale.
Adoption and proof loopMust be presentSetup success, repair commands, pilot reports, dashboard proof and PDF export.WhyThis turns a technical install into a buying process buyers can repeat internally.

Parity and wedge

Cover the must-have Sourcegraph workflows, then differentiate.

The point is not to clone Sourcegraph. The point is to make AI agents cheaper, faster and more governed with enough parity that enterprise buyers can compare.

WorkflowSourcegraph expectationAiIndexer implementation stance
Code searchSearch, regex, exact, file and language queriesKeep parity; make the result agent-packable.
Symbol navigationDefinitions, references, callers, callees and dependenciesKeep parity; feed blast radius and tests.
Deep SearchMulti-step research across reposDo it local-first with budget and citations.
Batch ChangesFind and change code across reposStart with Batch Autopilot dry-run, rollout gate and agent-reviewed patches.
Code InsightsSaved queries and trendsAdd token waste and adoption trends, not only code counts.
Code MonitoringAlerts on patterns and risky filesTie monitors to PR packs, governance and CI artifacts.
OwnershipCODEOWNERS and review routingUse owners in PR packs, batch runs and audit reports.
Permissions/auditEnterprise access controlsGovern context before it reaches an agent.
MCP/API/CLIIntegrations and automationKeep only five MCP tools; route internally to avoid schema bloat.
Agent adoptionNot usually the primary buying storyDetect whether Codex, Claude Code, Cursor, Windsurf, Copilot and Amp actually call MCP.
ROI proofNot the core Sourcegraph pitchAiIndexer lead: tokens avoided, loops killed, cost saved.
DeploymentCloud or enterprise installAiIndexer default: local/self-hosted, no source cloud by default.
PricingEnterprise platform pricingAiIndexer wedge: simple tiers and pilot proof before procurement.
Code searchExpectationSearch, regex, exact, file and language queriesAIndex stanceKeep parity; make the result agent-packable.
Symbol navigationExpectationDefinitions, references, callers, callees and dependenciesAIndex stanceKeep parity; feed blast radius and tests.
Deep SearchExpectationMulti-step research across reposAIndex stanceDo it local-first with budget and citations.
Batch ChangesExpectationFind and change code across reposAIndex stanceStart with Batch Autopilot dry-run, rollout gate and agent-reviewed patches.
Code InsightsExpectationSaved queries and trendsAIndex stanceAdd token waste and adoption trends, not only code counts.
Code MonitoringExpectationAlerts on patterns and risky filesAIndex stanceTie monitors to PR packs, governance and CI artifacts.
OwnershipExpectationCODEOWNERS and review routingAIndex stanceUse owners in PR packs, batch runs and audit reports.
Permissions/auditExpectationEnterprise access controlsAIndex stanceGovern context before it reaches an agent.
MCP/API/CLIExpectationIntegrations and automationAIndex stanceKeep only five MCP tools; route internally to avoid schema bloat.
Agent adoptionExpectationNot usually the primary buying storyAIndex stanceDetect whether Codex, Claude Code, Cursor, Windsurf, Copilot and Amp actually call MCP.
ROI proofExpectationNot the core Sourcegraph pitchAIndex stanceAiIndexer lead: tokens avoided, loops killed, cost saved.
DeploymentExpectationCloud or enterprise installAIndex stanceAiIndexer default: local/self-hosted, no source cloud by default.
PricingExpectationEnterprise platform pricingAIndex stanceAiIndexer wedge: simple tiers and pilot proof before procurement.

MCP surface contract

Keep exactly five MCP tools, but make every advanced workflow discoverable.

The web presentation mirrors the product contract: no schema bloat, no hidden action names, structured output for agents and readable fallback text for humans.

ToolActionsProduct job
contextautopilot | pack | cache | deep-search | pr-packBudgeted context, task packs, cache ordering, research and PR review artifacts.
searchauto | symbols | patterns | regex | exact | saved | cross-repo | batchSearch remains the substrate, but results feed packs, batch dry-runs and insights.
navigatereferences | callers | callees | definition | blast-radius | tests | ownership | auditGraph navigation powers risk, test prediction, review routing and governance checks.
statusfeatures | adoption | waste | roi | governance | insights | monitors | team-indexDiscovery and proof live in status so agents can self-diagnose and report value.
remembersave | search | history | session | outcomeRuns, decisions and outcomes become measurable local memory instead of chat residue.
contextActionsautopilot | pack | cache | deep-search | pr-packProduct jobBudgeted context, task packs, cache ordering, research and PR review artifacts.
searchActionsauto | symbols | patterns | regex | exact | saved | cross-repo | batchProduct jobSearch remains the substrate, but results feed packs, batch dry-runs and insights.
navigateActionsreferences | callers | callees | definition | blast-radius | tests | ownership | auditProduct jobGraph navigation powers risk, test prediction, review routing and governance checks.
statusActionsfeatures | adoption | waste | roi | governance | insights | monitors | team-indexProduct jobDiscovery and proof live in status so agents can self-diagnose and report value.
rememberActionssave | search | history | session | outcomeProduct jobRuns, decisions and outcomes become measurable local memory instead of chat residue.

Feature discovery

The features that make the comparison credible.

Autopilot, Context Packs, Team Shared Index, PR Packs, Governed Context, Batch Autopilot and Insights turn code intelligence into an agent-cost platform.

View all features
Autopilotpreview only

Agent Cost Autopilot

Give the agent a budgeted plan before it starts reading.

The first response tells the team how much context the agent would have burned and what it should read instead.

Naive context, required pack, savings, risk zones, files to read, files to avoid.

Pro · Beta · Pilot-grade · naive_tokens + required_pack_tokensEnabled: yes · Available: yes · Observed: no · Grade: Pilot-grade
Contextpreview only

Context Packs

Graph-aware task packs with exact symbol anchors, deps, tests, risks and cache classes.

A task becomes a reusable artifact that agents, CI and reviewers can consume without reconstructing context.

Each item carries fqn, path, line range, graph-aware reason, rank, token estimate, hash and cache class.

Pro · Beta · Pilot-grade · pack_items + fqnEnabled: yes · Available: yes · Observed: no · Grade: Pilot-grade
Contextpreview only

Cache-Aware Context

Order context so prompt caching can actually hit.

The buyer sees that AiIndexer reduces tokens and protects prompt-cache hit rate at the same time.

stable_tokens, volatile_tokens and cache_hit_estimate become first-class metrics.

Pro · Foundation · Foundation · stable_tokens + volatile_tokensEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Proofpreview only

Proof / ROI Dashboard

Show tokens avoided, cost saved, time saved and wasted reads.

Management gets numbers it can forward: tokens avoided, cost saved, time saved and loops killed.

Predicted vs observed savings, top repos, top agents, loops and export-ready summary.

Team · Beta · Pilot-grade · tokens_avoided + cost_savedEnabled: yes · Available: yes · Observed: no · Grade: Pilot-grade
Wastepreview only

Agent Loop Killer

Detect repeated reads, ignored packs and failing-test loops.

The dashboard catches the exact behavior teams complain about: repeated reads and tests without progress.

Findings include ingested agent transcripts, repeated files, ignored MCP, repeated tests and suggested next calls.

Pro · Foundation · Foundation · loop_findings + wasted_readsEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Adoptionpreview only

Agent Adoption Detector

Verify Codex, Claude Code, Cursor, Windsurf, VS Code, Zed, Copilot and Amp really call MCP.

Install success stops being a guess because every agent is checked against real MCP usage.

Reports configured yes/no, last MCP call, likely issue and idempotent repair command.

Pro · Foundation · Foundation · agent + configuredEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Teampreview only

Team Shared Index

One team index per commit instead of every dev indexing the same repo.

A CTO sees one commit-addressed index serving the team instead of every developer re-indexing locally.

Fresh/stale status, commit SHA cache, team ROI report and fallback to local if the server is unavailable.

Team · Foundation · Foundation · commit_sha + freshnessEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Reviewpreview only

PR Context Pack

Every PR gets provider-fetched changed files, blast radius, tests, owners and risks.

Reviewers get changed files, blast radius, tests, owners and sensitive risks before opening the diff.

Metadata-only provider context from gh/glab when available, CI artifact, review gate decision and optional GitHub/GitLab comment with reviewer summary.

Team · Foundation · Foundation · changed_files + provider_contextEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Governancepreview only

Governed Context

RBAC, redaction, audit logs and policy filters for agent context.

Security can prove which agent asked for which context and which paths were denied or redacted.

Audit log: agent, repo, request, pack, files, policy decision, redaction status and metadata-only export.

Enterprise · Foundation · Foundation · subject + policy_idEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Sales proofpreview only

Pilot Report

Generate a 30-minute report on the customer's real repos.

Sales can prove ROI on the customer's code before procurement turns the conversation into belief.

Files, symbols, reduction estimate, risks, adoption and baseline comparison.

Team · Foundation · Foundation · repos_scanned + symbols_mappedEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Searchpreview only

Deep Search

Iterative local research with evidence, citations and a stop condition.

Complex code questions become budgeted research with citations instead of another open-ended search loop.

Steps, evidence, citations, budget used and no-loop stop condition.

Pro · Foundation · Foundation · steps + evidenceEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Change managementpreview only

Batch Autopilot

Plan multi-repo changes with an enterprise rollout gate before opening PRs.

Teams get Sourcegraph-style migration planning without surprise PR storms or opaque rollout cost.

Repos touched, candidate patches, tests, owners, risks, PR metadata and a metadata-only rollout gate with CI conclusion.

Team · Foundation · Foundation · target_repos + candidate_changesEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Governancepreview only

Insights & Monitoring

Saved queries, trends and monitors for smells, deprecated APIs and token waste.

Saved searches become weekly signals for deprecated APIs, risky files, token waste and agent adoption.

Snapshots, trends, alerts and CI/webhook output.

Team · Foundation · Foundation · saved_query + snapshotEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Reviewpreview only

Ownership & Blast Radius

Resolve owners and show what a change can break.

Every risky change can name likely owners, downstream impact and the tests that protect it.

CODEOWNERS, git blame, path rules and team mapping feed PR packs and governance.

Team · Foundation · Foundation · owners + affected_symbolsEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Competitivepreview only

Sourcegraph Parity Layer

Cover the indispensable code intelligence workflows, then win on agent ROI.

The buyer recognizes the enterprise checklist, then sees AiIndexer win on agent cost proof.

Search, navigation, Deep Search, Batch, Insights, Monitoring, Ownership, permissions and API surfaces.

Team · Foundation · Foundation · parity_rows + wedge_rowsEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Adoptionpreview only

VS Code, CLI and MCP Surfaces

The same structured JSON powers CLI, MCP tools and IDE sidebars.

Every feature appears where agents are actually used: setup, CLI, MCP status, dashboard and IDE.

Feature registry feeds docs, CLI, MCP, dashboard, setup success and VS Code sidebar.

Free · Foundation · Foundation · feature_id + commandEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Navigationpreview only

Advanced Code Navigation

Architecture overview, dead code, smells, audit, duplicates, implementations, type hierarchy, map and rules in one router.

The customer can see what problem this workflow solves and how to prove it.

navigate routes architecture, dead-code, smells, audit, duplicates, implementations, type-hierarchy, map and rules through one metadata-only tool.

Pro · Foundation · Foundation · architecture + dead_codeEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Memorypreview only

Cross-Session Memory

Save and recall project observations across agent sessions instead of re-deriving them.

The customer can see what problem this workflow solves and how to prove it.

remember saves, searches and replays observations with run-outcome capture, all stored locally.

Pro · Foundation · Foundation · observation + recall_hitsEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Searchpreview only

Batch Search Tools

Run many searches in one routed call to cut round-trips and tokens.

The customer can see what problem this workflow solves and how to prove it.

search action=batch groups related queries with shared ranking and a single budgeted response.

Pro · Foundation · Foundation · batch_queries + grouped_resultsEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Deploymentpreview only

Self-Hosted & Air-Gapped

Run the whole index, context and proof stack locally with no network egress.

The customer can see what problem this workflow solves and how to prove it.

Local SQLite index, no-network mode, metadata-only exports and a doctor check that proves air-gapped operation.

Enterprise · Foundation · Foundation · no_network + local_sqliteEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Interoppreview only

Code Graph Export

Export the code graph as SCIP/LSIF or native full-fidelity AIndex Graph (.aig).

The customer can see what problem this workflow solves and how to prove it.

scip and graph subcommands export/import SCIP/LSIF interop indexes and native .aig full-fidelity graphs.

Free · Foundation · Foundation · scip_export + aig_exportEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Navigationpreview only

Auto-Wiki

Generate a deterministic, metadata-only code wiki from the live graph.

The team gets an always-fresh, publishable architecture wiki without writing or maintaining one.

Index + per-module pages with signatures, structure and optional execution flows are rendered from the graph; never raw source bodies.

Pro · Foundation · Foundation · wiki_pages + module_pagesEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Reviewpreview only

Change Coupling

Surface files that historically change together as a git co-change blast-radius signal.

The agent sees the files that git history says change together before it edits one side of a coupled pair.

Git history is parsed into bounded co-change pairs and surfaced alongside pivots so the agent sees coupled neighbors before editing.

Pro · Foundation · Foundation · co_changes + pair_countEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Contextpreview only

One-Call Context Pipeline

Capsule, impact, memory recall and change-coupling in a single MCP call.

One context call returns the capsule, impact, recalled insights and co-changed files, so the agent edits without round-trips.

A single context call returns the capsule, impact, prior insights (memory) and co-changed neighbors, each bounded and degrading to empty when unavailable.

Pro · Foundation · Foundation · capsule + impactEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Governancepreview only

Enterprise Access Control

RBAC, SSO and SCIM provisioning for enterprise teams.

Security and IT see RBAC, SSO and SCIM gated to Enterprise and enforced through governance policy.

Role-based access control, single sign-on and SCIM user provisioning are gated as Enterprise entitlements and enforced against the governance policy surface.

Enterprise · Foundation · Foundation · rbac_roles + sso_providerEnabled: yes · Available: yes · Observed: no · Grade: Foundation
Comprehensionpreview only

Codebase Atlas

Understand any AI-built codebase: what it is, what it does, how it's built, what's at stake, and how it all connects.

A team that built fast with AI finally sees what the codebase is, what it does, where the risk concentrates and how it all connects.

Atlas builds a deterministic, metadata-only model of the codebase: subsystems and their purpose, a capability-vs-claims drift report, a ranked risk board, and cross-surface traceability from one local run.

Pro · Foundation · Foundation · system_model + drift_reportEnabled: yes · Available: yes · Observed: no · Grade: Foundation