CODEBASE INTELLIGENCE

Your code has a memory now.

Axon builds a living knowledge graph of your project — every dependency, every pattern, every tacit rule. Then it compiles precisely the context an AI agent needs to write code that actually works.

Explore Capabilities See How It Works
axon — session
# Analyze. Brief. Execute. Verify.
$ axon init -p ./my-project
 Graph: 847 nodes, 2341 edges
 12 constraints discovered

$ axon session "Add rate limiting to /api/upload"
 Brief compiled — 2847 tokens, 14 files
 3 forbidden moves identified
 Executing via claude-code...
 Verification passed: tsc ✓  tests ✓
 Attribution: 4 files modified, 0 regressions
Intelligence at every layer.
Not another wrapper. Axon understands your codebase structurally — then uses that understanding to make AI coding actually reliable.

Knowledge Graph

Static analysis + git history fused into a typed graph. Every artifact, dependency, co-modification pattern, and ownership signal — queryable and always current.

Context Compiler

Task-specific briefs assembled from the graph. Seed resolution, dependency slicing, budget enforcement. The AI gets exactly what it needs — nothing more, nothing less.

Forbidden Moves

Briefs include constraints the AI must not violate: owned files, invariants, failure modes. Mistakes are prevented before they happen, not caught after.

Verification Loop

Every execution is followed by automated verification — type checks, tests, custom commands. Failures trigger retry with enriched context, not blind repetition.

Tacit Knowledge Engine

Learns unwritten rules from failures and patterns. Hypotheses are generated, validated by humans, and promoted to operational constraints that shape future briefs.

Provider Routing

Claude Code, Codex CLI, or any future provider — same execution contract. The orchestrator picks the right tool for each sub-task, not a one-size-fits-all model.

From intent to verified code.
Four stages. Zero hand-holding. The graph does the thinking so the agent can do the coding.
1

Analyze

Static analysis via ts-morph + git history builds a typed knowledge graph. Every function, import, dependency, co-modification pattern, and ownership signal is captured as nodes and edges.

2

Compile

Given a task description, the compiler resolves seed artifacts, traverses the graph with task-type-specific strategies, and assembles a CompiledBrief — token-budgeted, priority-ordered, with forbidden moves and invariants.

3

Execute

The brief is injected as structured context into a CLI provider session. The agent writes code with full awareness of constraints, dependencies, and failure patterns — not just the file it's editing.

4

Verify & Learn

Automated verification runs type checks and tests. Failures feed back into the TKE as learning events, generating hypotheses about what went wrong. The graph gets smarter with every task.

Built to run.
A persistent daemon with Unix socket IPC, WAL-based persistence, and a conversational gateway for remote orchestration.
Analyzers
Knowledge Graph
Context Compiler
Provider Router
Verifier
TKE
Orchestrator
Concierge Gateway
Telegram / Mini App

Every component communicates through typed Zod-validated protocols. The graph is the single source of truth.

440+
Tests Passing
9
Phases Complete
6
Node Types
11
Edge Types
10
Task Types

Stop prompting.
Start briefing.

Give your AI agents the context they deserve. Axon turns a raw codebase into an execution surface that can actually guide autonomous work.