Eidon runs 11 layers of structural analysis on your entire codebase and compresses the full architecture into a single, compact graph. Every AI tool you use gets the real picture.
Install freeYour AI reads files one by one, hits the token ceiling, and starts filling in the rest with confident guesses.
Eidon compresses your entire architecture into a 4-dimensional graph. Every relationship preserved. Your AI receives exactly what it needs, nothing wasted.
RAG search retrieves text fragments. The moment it does, structural relationships are gone. File listing overflows tokens after a few dozen files. Neither approach sees your codebase as a system.
So your AI fills gaps with confident guesses. It's wrong about the things that matter: blast radii, critical paths, what breaks when you change something.
Eidon runs 11 layers of deterministic analysis: architecture, data flow, risk scoring, git history, error propagation, test coverage. The result is a 4-dimensional structural graph using graph-theoretic compression.
A 6,500-file repository compresses to 12,000 tokens. Every architectural relationship preserved. Your AI receives the shape of your system, not a sample of it.
Four scenarios from actual codebases. All invisible without Eidon.
Your AI suggests the refactor. It sees the function. It doesn't see what depends on it — the 8 direct callers, the 34 transitive ones, the 0 tests covering any of them.
Eidon maps the full blast zone before you touch anything. Not a guess — a mathematical BFS over the live dependency graph. Every dependent, ranked by cascading risk.
Dead code isn't just wasted lines — it's active noise. Your AI includes zombie functions in its analysis, refactors them, documents them. On every run.
Eidon's AI Court verifies dead code with hard evidence. Zero call edges in the graph. Zero imports from other modules. Cross-checked. Not a heuristic — a verdict.
.env files are gitignored, invisible to your AI. It writes code referencing variables that don't exist in production. Silent failures. Runtime crashes. Missing docs.
Eidon scans every process.env reference across your entire codebase and cross-maps it to your env files. Missing vars flagged. Critical vs optional, ranked.
Your CI checks syntax and logic. It doesn't check if the changed file is a single point of failure with 47 dependents and zero test coverage. A green checkmark isn't safety.
One line in your CI config. eidon gate runs in under a second, reads from the context brain, exits 1 if structural risk exceeds your threshold. No new infrastructure.
Works inside the tools you already use
npm install -g eidon — that's it. A native binary drops into your PATH. No Docker. No cloud. No runtime after install.
Architecture, dependencies, risk, error propagation, test coverage, git history. Eidon compresses it like JPEG compresses images. Your 6,500-file project becomes 12,000 tokens of pure structure.
Eidon plugs into every AI tool via MCP. Token limits still exist, but Eidon picks exactly what matters. Ask "what breaks if I change this?" and get a real answer.
Run eidon analyze once. These four run in under a second, every time after.
eidon doctor
Health score, top risks, SPOFs, test gaps. Know the exact state of your codebase before the first line of AI output.
eidon review
For each changed file: blast radius, SPOF status, test coverage, active findings. Structural data, not opinion.
eidon gate
Structural risk gate for CI/CD. Exits 1 if a changed file crosses your risk threshold. Blocks the PR. One line.
eidon diff
Baseline your architecture. Then measure drift: Fiedler value, entropy delta, SPOF count, community fragmentation.
This is not RAG. Not summarization.
This is your codebase, understood.
Enterprise teams choose Eidon because your code never touches our servers. Every byte stays on your machine.
All processing happens on your machine. LLM calls go from you to your provider. OpenRouter, OpenAI, Anthropic, or Ollama.
No analytics. No crash reports. Eidon never phones home. Nothing is tracked.
Every release ships with a SHA-256 checksum. The installer verifies it before writing anything to disk. Tampered binaries are rejected before they run.
For personal projects. No time limit.
For devs who need the full power.
For teams with secrets to protect.
AI tools like Copilot and Cursor only read the files you have open. On a project with hundreds or thousands of files, that means they're mostly guessing. Eidon solves this by building a full index of your codebase and serving it to your AI on demand.
Never. Eidon builds its index entirely locally. Your source code is never sent to us. The only external calls are from you to your LLM provider (OpenRouter, OpenAI, Anthropic, or a local Ollama instance).
Yes. Eidon uses a tiered indexing system designed for large monorepos. It prioritizes the most relevant files and compresses intelligently to fit within your AI's context window.
No. Run the one-line installer, then eidon init. Everything is self-contained and runs locally. No Docker. No cloud. No configuration headache.
Type it from memory. No URL. No flags. No platform detection.
npm install -g eidon
eidon init
eidon analyze
eidon install-mcp
That's it. Your AI tools now query Eidon automatically via MCP.
Every answer they give knows your full codebase.
Free forever for personal projects. No credit card. No Docker. No telemetry.