GreyMatter

Your AI has amnesia. Fix it.

What if your AI actually got smarter every session instead of starting over?

Get Started GitHub
Install in 2 minutes click to copy
$ curl -sSL greymatter.axiomworks.ai/install | bash

Every AI session starts at zero.

Your architecture decisions, your coding patterns, your preferences — gone. Every session, you re-explain. Every session, your AI starts as a stranger.

Context windows aren't memory. They're a junk drawer that empties when you close the tab. GreyMatter fixes this.

The System — How It All Works

GreyMatter isn't a chatbot. It's the infrastructure that turns AI coding agents into an autonomous development platform.

AI Coding Agents
Claude Code, Codex CLI, or Gemini CLI. GreyMatter doesn't replace them — it gives them a persistent brain, a work queue, and parallel sessions.

You already use AI to write code. But every session starts from scratch — no memory of what worked, what broke, or how your project is structured.

GreyMatter wraps around your existing AI agent. When it starts, GreyMatter injects your project's knowledge: past bugs, architecture decisions, coding patterns, and active work items. Your AI starts informed, not empty.

Works with: Claude Code, OpenAI Codex CLI, Google Gemini CLI — any tool that supports the MCP protocol.

Click to collapse ↑

Click to learn more ↓
Go Coordinator
A compiled binary that manages work dispatch, session lifecycle, quality gates, and health monitoring. Runs as a system service.

The coordinator is the brain behind the operation. It decides what gets built, dispatches work to agents, and verifies quality before code ships.

Work dispatch: Submit a task, and the coordinator assigns it to an available agent. Run up to 8 agents in parallel.

Quality gates: Every completion runs through a tiered eval pipeline — compile, test, lint (Tier 1), then structural analysis (Tier 2). Bad code gets rejected automatically.

Auto-push: When code passes all gates, it's pushed to GitHub automatically. No commits sitting on disk.

Click to collapse ↑

Click to learn more ↓
MCP Plugin
20+ tools your AI calls naturally during conversation. Save knowledge, search memory, dispatch agents, scan for secrets. Your AI just remembers.

MCP (Model Context Protocol) is how AI tools communicate. GreyMatter's plugin gives your AI 20+ tools it can call as naturally as reading a file or running a command.

Memory tools: gm_knowledge — search, create, and manage knowledge entries. gm_observe — capture observations from sessions.

Work tools: gm_work — create and manage work items. gm_dispatch — spawn agents to build in parallel.

Quality tools: gm_standards — enforce team rules. gm_security — scan for PII, secrets, and vulnerabilities.

Click to collapse ↑

Click to learn more ↓
SQLite + Ollama
Your second brain. A local database stores everything. Ollama runs semantic search — finding related knowledge by meaning, not keywords.

Everything GreyMatter knows lives in a single SQLite database on your machine. Nothing leaves your computer. No cloud. No telemetry.

What it stores: Observations, patterns, corrections, expertise, quality standards, work items, and session history. Over 10,000 entries in a production system.

Semantic search: Ollama runs nomic-embed-text locally. Ask "how do we handle auth?" and find entries about JWT, OAuth, session cookies, and SAML — even if those words don't appear in your query.

Encryption at rest: Optional SQLCipher encryption with FIPS 140-3 compatible key derivation. Your knowledge, protected.

Click to collapse ↑

Click to learn more ↓
You
AI Coding Agent
MCP Plugin
Go Coordinator
Dispatch • Sessions • Quality Gates
Second Brain
SQLite • Ollama • Knowledge Graph
Session 1
Project A
Session 2
Project B
Session 3
Project C

A Second Brain, Not a Context Window

GreyMatter models memory the way your brain does. Important knowledge gets reinforced. Stale knowledge decays naturally.

Spaced Repetition (FSRS-6)
Following the same forgetting curves Ebbinghaus documented in 1885. Your AI's memories age like yours do. The important ones get stronger.

Your brain doesn't remember everything equally. Important memories get reinforced; unimportant ones fade. GreyMatter works the same way.

Every knowledge entry has a stability score that increases when it's used and decreases over time. The algorithm (FSRS-6) is the same one used by Anki, the most popular flashcard app in the world — proven by millions of users since 1885.

In practice: A bug fix you applied yesterday has high retention. An architecture decision from 3 weeks ago starts fading — unless your AI uses it, which resets the clock. Knowledge that matters stays; knowledge that doesn't, gracefully decays.

Click to collapse ↑

Click to learn more ↓
Five Memory Types
Observations, patterns, expertise, corrections, and gotchas. Each type has different decay rates and promotion paths.

Not all knowledge is equal. A "this crashed the server" correction is more urgent than a "we prefer tabs over spaces" pattern. GreyMatter categorizes automatically:

Observations — raw data captured from sessions. High volume, fast decay. The raw material.

Patterns — recurring behaviors detected across sessions. "This team always writes tests first." Medium decay.

Expertise — deep technical knowledge. "FIPS 140-3 requires NIST-approved algorithms." Slow decay.

Corrections — mistakes and fixes. "Never use shell=True." Fast decay (bugs get fixed).

Gotchas — traps the team has hit. "macOS kills unsigned binaries with SIGKILL." Medium decay.

Click to collapse ↑

Click to learn more ↓
Semantic + Full-Text Search
Two search modes, both local. FTS5 for keywords, Ollama for meaning. Ask "how do we handle auth?" and find JWT, OAuth, and session cookie entries.

Traditional search finds exact words. Semantic search finds meaning. GreyMatter does both, and both run locally on your machine.

Full-text search (FTS5): Instant keyword matching across all knowledge. Type "database" and find every entry mentioning databases.

Semantic search (Ollama): Ask a question in plain English. "How do we handle user authentication?" finds entries about JWT tokens, OAuth flows, session cookies, and SAML — even if those exact words aren't in your query. Powered by nomic-embed-text running locally via Ollama.

Nothing leaves your machine. No cloud API calls. No data sent to embedding services. Your knowledge stays yours.

Click to collapse ↑

Click to learn more ↓
Cross-Session Consolidation
After each session, GreyMatter detects contradictions and promotes stable observations into permanent expertise. Like sleep consolidation for your AI.

When you sleep, your brain consolidates memories — strengthening important ones, discarding noise, and resolving conflicts between competing memories. GreyMatter does this after every AI session.

Contradiction detection: If a new entry says "coordinator runs on Mac Mini" but an old entry says "coordinator runs on agenticai2," the older entry gets flagged as stale. No more acting on outdated information.

Observation promotion: When the same observation appears across multiple sessions, it gets promoted from a fleeting observation to a confirmed pattern, and eventually to permanent expertise.

The result: Your AI's knowledge self-curates. Important things get stronger. Outdated things fade. You never have to manually clean up your knowledge base.

Click to collapse ↑

Click to learn more ↓

Your live dashboard, every session

GreyMatter adds a status line to every Claude Code session. At a glance: what your AI knows, what it's working on, and whether it's safe. Tell Claude “explain the status line” and it will walk you through it.

Terminal — ~/my-project
you@dev:~/my-project$ claude
▾ Claude Code v2.2.0
/help for commands • /mcp to see tools • type your request to begin
✓ GreyMatter — 20 tools loaded • 156 memories injected • 5 quality standards active
What would you like to work on?
↓ THE STATUS LINE — always visible at the bottom of your session
* 42obs +3/hr . 156know +8/hr . 12pat +1/hr . 5std | 3 fading | auto . P:2 . W:1 . 2/4agents | Gate 12+ 1x | > 8scans | CTX 72%

The status line appears in every Claude Code session with GreyMatter installed.

Brain Metrics
42obs +3/hr . 156know
Observations, knowledge entries, patterns, and quality standards. The +N/hr shows your AI is actively learning.
Answers: “Is my AI learning from my work?”
Knowledge Recall
3 fading
FSRS-6 spaced repetition tracks which knowledge entries need review before they decay. Confirm to strengthen retention.
Answers: “Is anything about to be forgotten?”
Work Pipeline
auto . P:2 . W:1 . 2/4agents
Dispatch mode (auto/supervised/planned), pending items, active work, and agent capacity. Your autonomous dev team at a glance.
Answers: “What’s in the queue?”
Quality Gates
Gate 12+ 1x
Passes and failures from the tiered eval pipeline. Code gets compiled, tested, linted, and structurally reviewed before merge.
Answers: “Is my code being reviewed?”
Security Scans
> 8scans
SecureLLM intercepts every LLM call. Scans for PII, secrets, prompt injection, and policy violations. Blocked calls show in red.
Answers: “Am I safe?”
Context Pressure
CTX 72%
How full the context window is. GreyMatter auto-compacts at 80% to preserve quality. Green < 60%, yellow < 85%, red = critical.
Answers: “How much context is left?”

Everything you need. Nothing you don't.

Local-First
One SQLite database. On your machine. Nothing sent to any server, ever. Data sovereignty solved at the design level.
Knowledge Graph
Observations become patterns. Patterns become expertise. Duplicates detected. Contradictions resolved. Your AI gets smarter the more you use it.
Session Orchestration
The Go coordinator spawns multiple AI sessions across projects. Each runs in tmux, works autonomously, commits code, and reports back.
20 MCP Tools
Deep integration via Model Context Protocol. Memory, work queue, security, agents — all through natural conversation with Claude, Codex, or Gemini.
Multi-LLM Support
Works with Claude (Anthropic), OpenRouter models, and Ollama local inference. Route to the right model for the right task. Cost tracking built in.
BSL 1.1 Licensed
Source code is public. Read it, fork it, learn from it. Free for individuals. Source converts to Apache 2.0 after the Change Date.

Every. Single. LLM Call. Scanned.

Every line of code your AI writes passes through an LLM. What else passes through? Your API keys. Your database credentials. Your customers' PII.

PII Detection
SSNs, credit cards, API keys, AWS credentials, private keys, phone numbers — caught and redacted before the model sees them.
Prompt Injection Guard
Instruction override, system prompt extraction, role hijacking, delimiter attacks — blocked at the gate.
Encryption at Rest
SQLCipher support for encrypted database storage. ML-KEM-768 post-quantum key encapsulation available.
Append-Only Audit Trail
Every scan logged. Every block recorded. Full forensic history in your local database. Security runs on every interaction by default.

SecureLLM is also available as a standalone product. Learn more →

Not One Assistant — A Fleet

An agent without context is just a fancy autocomplete. GreyMatter agents carry "souls" — persistent identity documents with domain expertise, coding standards, common patterns, and failure modes.

When GreyMatter dispatches a work item, it matches the task to the right expert. A Rust issue gets the Rust expert. A React component gets the TypeScript expert. The right brain for every job.

Autonomous work queue: Submit tasks, set priorities, walk away. Agents execute in parallel, run quality gates, and generate follow-up work items when something fails.

Create your own experts by dropping a markdown file in ~/.greymatter/soul/experts/

GreyMatter Solo & Teams

GreyMatter Solo GMS
Your personal second brain. Everything runs on your machine, controlled by you.
  • Full knowledge graph with spaced repetition
  • Go coordinator with session dispatch
  • 20 MCP tools for Claude, Codex, and Gemini
  • SecureLLM security on every interaction
  • Works fully offline — no internet required
GreyMatter Teams GMT
Your team's collective intelligence. Share knowledge with encryption and access controls.
  • Everything in Solo, plus team synchronization
  • Encrypted knowledge sharing with retractable access
  • mTLS on all inter-node communication
  • Quality gates that review AI-generated code
  • Air-gapped and enterprise deployment support

SDK, API & MCP

GreyMatter isn't just a tool — it's a platform. Three transports, one API:

MCP — 20 tools that integrate directly with Claude Code, Codex CLI, and Gemini CLI. Memory, work queue, security, agents — all through natural conversation.

REST API — The Go coordinator exposes a full REST API. Access GreyMatter from any web app, mobile app, or dashboard. Every endpoint secured by API key + rate limiting.

Python SDK — Import GreyMatter directly into your Python 3.12+ applications. Six namespaces: gm.knowledge, gm.work, gm.agents, gm.security, gm.sync, gm.config.

Up and running in two minutes.

1. Install GreyMatter

curl -sSL greymatter.axiomworks.ai/install | bash

Checks for Claude Code, downloads GreyMatter, sets up your database, configures the MCP plugin. Two minutes.

2. Log into Claude Code

With an API key: export ANTHROPIC_API_KEY=your-key — or with Claude Pro: /login

3. Open your project and start Claude

cd your-project && claude — 20 tools loaded automatically. Type /mcp to see them.

4. Optional: Local LLM for semantic search

Ollama enables vector search. GreyMatter works without it (keyword search only).

curl -fsSL https://ollama.com/install.sh | sh && ollama pull nomic-embed-text