Auto-builds a budgeted capsule for the task: full source for the few pivotal symbols, compact signatures for neighbors — typically 4–8k tokens instead of 20–50k.
Product
Your agent finally understands your whole codebase.
AIndex builds a dependency graph of your repo on your machine, then serves your AI agent — over MCP — the exact connected code each task needs. No more pasting files and hoping.
What it does
Five capabilities your agent gets the moment you install.
Find any symbol by name, kind or meaning across the whole project in about 15ms.
See the blast radius of a change — exactly what breaks if your agent touches a symbol — before a single line is edited.
Insights and decisions persist between sessions, and automatically go stale when the underlying code changes.
One setup command wires it into Codex, Claude Code, Cursor, Windsurf, VS Code and Zed.
Your code is indexed on your machine. Nothing is uploaded, no telemetry — only license activation touches the network.
What ships
A real local engine, not a loose prompt pack.
You get a signed binary, the MCP server with five tools, one-command agent setup, and machine-readable JSON for automation — all running locally.
Context pipelinerepo -> graph -> agent
Five tools, one server
context, search, navigate, remember and status — your agent calls them directly over MCP instead of asking you to run commands.
Real dependency graph
Ranks code by importance, traces calls and architecture, finds dead code and duplicates, and shows the impact of any change.
One setup command
Codex, Claude Code, Cursor, Windsurf, VS Code and Zed get generated config — with rollback if you change your mind.
Private project memory
Indexes, repo profiles and cross-session memory live in a local SQLite store, with import/export for migration.
Native agent workflow
You install once. The agent uses it quietly.
AIndex should remove work, not add ceremony — so it indexes 10k files in about 8 seconds and answers a context query in about 15ms.
- Install
One command verifies the Ed25519 signature and checksum, then places the binary on PATH.
- Onboard the repo
AIndex detects the project, builds the dependency graph and writes agent config — re-indexing incrementally in about 50ms after edits.
- Ask your agent normally
The agent pulls the exact connected context through MCP tools instead of relying on pasted files.
- Verify and recover
status, JSON outputs and clean uninstall paths make the index health visible and every step reversible.
Why it matters
Less guessing. Fewer tokens. Code that holds together.
Agents that read the graph, not just the file
AIndex ranks code by who-calls-what and is test-aware, so your agent works from the real implementations and their true dependencies — not whatever happened to be open.
Up to 74% fewer tokens per task
Tiered context means smaller prompts, lower bills, and far more work done before you hit the context limit.
Private by default
No hosted index, no source upload. The engine runs entirely on your machine; only license activation ever talks to the network, and Free is fully offline.
Give your agent a real map of your code.
Free to start. No credit card. Your code never leaves your machine.