https://github.com/AVIDS2/memorix

Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro, OpenCode, and Trae.
https://github.com/AVIDS2/memorix

agent-memory ai-coding antigravity claude-code codex coding-agents copilot cross-agent-memory cursor gemini-cli hermes-agent local-first mcp mcp-server model-context-protocol oh-my-pi openclaw opencode typescript windsurf

Last synced: 1 day ago
JSON representation

Host: GitHub
URL: https://github.com/AVIDS2/memorix
Owner: AVIDS2
License: apache-2.0
Created: 2026-02-14T06:53:17.000Z (5 months ago)
Default Branch: main
Last Pushed: 2026-07-07T10:56:35.000Z (6 days ago)
Last Synced: 2026-07-07T11:16:50.302Z (6 days ago)
Topics: agent-memory, ai-coding, antigravity, claude-code, codex, coding-agents, copilot, cross-agent-memory, cursor, gemini-cli, hermes-agent, local-first, mcp, mcp-server, model-context-protocol, oh-my-pi, openclaw, opencode, typescript, windsurf
Language: TypeScript
Homepage:
Size: 10.6 MB
Stars: 525
Watchers: 4
Forks: 40
Open Issues: 5
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- License: LICENSE

Awesome Lists containing this project

awesome-agent-harness - GitHub - 510-f4b400?style=flat-square)](https://github.com/AVIDS2/memorix) | memory, mcp, cross-agent | Local-first cross-agent memory control plane with MCP support, workspace sync, sessions, and orchestration state. | (Catalog / Context & Working-State Engineering)

README

Memorix

Local-first shared memory layer for AI coding agents.

One project memory system for Claude Code, Codex, Cursor, Windsurf, Copilot, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, and any MCP-capable agent.

---

Memorix gives the AI coding agents you already use a shared, searchable project memory that survives new chats, IDE switches, terminal sessions, and handoffs. The memory lives under the Git project, not inside one chat window or one tool.

Use Claude Code today, Codex tomorrow, and Cursor in the afternoon. The agent can change; the project memory stays the same.

**Use Memorix when** you keep re-explaining the same project to a new agent session: the last session already figured something out, another IDE cannot see it, or a design decision is buried in a chat you cannot find anymore.

| Problem | What Memorix adds |
| --- | --- |
| The next session forgets what the last session learned | Project-scoped memory, session summaries, timelines, and detail retrieval |
| Different agents know different things | One local memory pool available through MCP, hooks, CLI, SDK, and the bundled terminal agent |
| Git records what changed, but agents cannot recall it well | Git Memory turns commits into searchable engineering facts |
| Architecture decisions disappear into old chats | Reasoning Memory stores why choices were made, with alternatives and trade-offs |
| Static rule files drift | Gotchas, fixes, and project skills evolve from real work |
| Parallel agent work gets messy | `memorix orchestrate` coordinates task context, handoffs, locks, verification, and review loops |

Memorix is local-first. SQLite is the canonical store, Orama handles search, and LLM-backed formation/embedding is optional. Without model keys, Memorix still works with local full-text retrieval.

### Capabilities

Memorix is more than a memory store. It also installs agent integrations, keeps useful work events, turns commits into project facts, exposes a local control plane, and can coordinate multi-agent work when a task needs it.

| Capability | What it does | Entry point |
| --- | --- | --- |
| Memory Autopilot | A task-shaped project brief for a new agent session, with start files, trusted memories, cautions, and verification hints | `memorix context --task "..."`, `memorix_project_context` |
| Observation Memory | Searchable facts, fixes, gotchas, session summaries, and implementation notes scoped to the current Git project | `memorix memory`, MCP memory tools |
| Code Memory | File/symbol links and freshness checks so old memories point to current code or show up as suspect/stale | `memorix codegraph`, automatic context refresh |
| Git Memory | Commit-derived engineering facts that answer what changed, where, and why it matters | `memorix ingest commit`, git hook |
| Reasoning Memory | Design rationale, alternatives, trade-offs, and risks that should survive beyond one chat | `memorix reasoning`, memory formation |
| Agent setup | One setup path for MCP, rules, hooks, skills, plugins, bundles, or extensions depending on the agent | `memorix setup --agent ` |
| Agent doctor | Checks whether agent MCP config and guidance are current, then repairs Memorix-owned entries when needed | `memorix doctor agents`, `memorix repair agents` |
| Hooks and skills | Optional capture from supported agents, plus reusable project skills promoted from durable knowledge | `memorix hooks`, `memorix skills` |
| Dashboard and HTTP | A local web UI and shared MCP endpoint for browsing memory, project state, teams, and diagnostics | `memorix dashboard`, `memorix background start` |
| Orchestration and team work | Task planning, worker handoffs, file locks, messages, verification gates, and review loops | `memorix orchestrate`, `memorix team`, `memorix lock` |
| memcode | A bundled terminal coding agent that already reads and writes the same project memory | `memorix`, `memcode` |
| CLI and SDK | Scriptable access for automation, imports/exports, diagnostics, and custom integrations | `memorix ...`, `createMemoryClient()` |

Memorix connects through the interfaces each agent already supports: plugin packages, MCP, project rules, hooks, skills, or the bundled terminal agent. `memorix setup` chooses the right setup for each agent and keeps stdio MCP as the default transport.

Claude Code

_{official plugin + MCP + hooks + skills}

Codex CLI

_{official plugin + MCP + AGENTS.md}

GitHub Copilot CLI

_{plugin + MCP + hooks + skills}

Cursor

_{MCP + rules + skills}

Windsurf

_{MCP + rules + hooks}

Gemini CLI

_{extension + MCP + hooks + skills}

OpenCode

_{local plugin + MCP + skills + AGENTS.md}

pi coding agent

_{package + extension + skill}

Kiro

_{MCP + steering + hooks}

Antigravity

_{plugin + MCP + hooks + skills}

Trae

_{MCP + project rules}

memcode

_{bundled terminal agent}

OpenClaw

_{bundle + MCP + hooks + skills}

Hermes Agent

_{plugin + MCP + hooks + skills}

Oh-my-Pi

_{package + MCP + hooks + skills}

Any MCP Client

_{stdio or HTTP MCP}

_{Works with agents that speak MCP, expose hooks/rules, or support plugin/package entries. One local-first memory layer shared across all of them.}

Integration surfaces:

| Surface | What it does | Memorix entry |
| --- | --- | --- |
| Setup command | Installs the recommended one-time user-level Memorix integration | `memorix setup --agent --global` |
| MCP | Gives an agent compact Memorix tools for project context, search, detail retrieval, storage, and resolution | bundled in setup packages or `memorix serve` |
| Usage guidance | Teaches an agent when and how to use Memorix without forcing memory lookup on every prompt | bundled or generated by `memorix setup` |
| Hooks | Optional auto-capture of prompts, tool events, file edits, and session lifecycle events where the agent exposes hooks | bundled or generated by `memorix setup` |
| Plugin or bundle package | Installs plugin, compatible-bundle, or package files where the agent supports them | Claude Code, Codex, GitHub Copilot CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi |
| Extension | Installs extension files where the agent supports them | Gemini CLI |
| Local plugin | Installs local plugin files where the agent loads them directly | OpenCode |
| MCP/rules config | Writes MCP, rules, steering, guidance, or hook config for IDEs and agents that expose those surfaces | Cursor, Windsurf, Kiro, Trae |
| Skills | Turns durable project knowledge into reusable task guidance | `memorix skills` and `memorix_promote` |
| memcode | Opens the bundled terminal agent that already uses Memorix memory | `memorix` or `memcode` |

See [Integration Surfaces](docs/INTEGRATIONS.md) for the current support matrix and what each generated file means.

Use the same setup command without `--global` only when you intentionally want repo-local guidance, rules, or hooks in the current Git project.

CLI, MCP, and HTTP are different entry points:

- `memorix` CLI is the direct command surface for setup, memory search/store, Git Memory, import/export, dashboard, orchestration, diagnostics, and automation.
- `memorix serve` is the stdio MCP bridge used by IDEs and coding agents. Its default tool profile is `micro`, so agents see only the compact core tool set.
- `memorix background start` / `memorix serve-http` run the HTTP service for a shared endpoint, dashboard, Docker, or multiple clients.

Requirements:

- Node.js `>=22.18.0`
- Git, because project identity is derived from the real Git root

Install and initialize:

```bash
npm install -g memorix
memorix init --global # optional defaults
memorix setup --agent claude --global # or codex, copilot, cursor, pi, gemini-cli, opencode,
# windsurf, kiro, antigravity, trae, openclaw, hermes, omp
```

`memorix init` is optional. It creates or updates TOML configuration:

- `~/.memorix/config.toml` for global defaults
- `/memorix.toml` for optional project overrides

Legacy `memorix.yml`, `.env`, and `~/.memorix/config.json` are still read for compatibility, but new setup flows use TOML.

If you want repo-local guidance or hooks for a specific repository, run the same setup command from inside that repo without `--global`.

### Connect an existing agent

Use the setup command first. The global form is the normal one-time install:

```bash
memorix setup --agent claude --global
memorix setup --agent codex --global
memorix setup --agent copilot --global
memorix setup --agent cursor --global
memorix setup --agent pi --global
memorix setup --agent gemini-cli --global
memorix setup --agent opencode --global
memorix setup --agent windsurf --global
memorix setup --agent kiro --global
memorix setup --agent antigravity --global
memorix setup --agent trae --global
memorix setup --agent openclaw --global
memorix setup --agent hermes --global
memorix setup --agent omp --global
```

What it installs depends on the target agent, but the goal is the same: make Memorix available wherever you open that agent without asking you to wire every repo by hand.

- Claude Code: installs the Memorix plugin package, adds `CLAUDE.md` guidance, and enables hook capture when you do not pass `--noHooks`.
- Codex: installs the Memorix plugin package, adds `AGENTS.md` guidance, and enables hook capture when you do not pass `--noHooks`.
- GitHub Copilot CLI: installs the Copilot plugin package and official Memorix skills.
- Pi: installs the user-level Pi package and official skills.
- Cursor: writes Cursor MCP/rules/config entries in the chosen scope.
- Gemini CLI: installs the extension package, `GEMINI.md` context, hooks, and skills. Antigravity CLI has an official Gemini CLI migration path, but Gemini CLI remains an active standalone target.
- OpenCode: installs the local plugin file, `opencode.json`, skills, and `AGENTS.md` guidance.
- Windsurf, Kiro, Trae: write the MCP/rules/hooks files the target supports.
- Antigravity: installs the official plugin package with `plugin.json`, `mcp_config.json`, `hooks.json`, rules, and skills under `~/.gemini/config/plugins/memorix` or `.agents/plugins/memorix`.
- OpenClaw: installs an OpenClaw-compatible bundle with `.mcp.json`, official skills, and an OpenClaw `HOOK.md`/`handler.ts` hook pack.
- Hermes Agent: installs into Hermes home (`%LOCALAPPDATA%\hermes` on native Windows, `~/.hermes` elsewhere, or `HERMES_HOME`), enables the plugin in `config.yaml`, registers plugin hooks, slash/CLI commands, skills, and writes MCP config.
- Oh-my-Pi: installs an `omp.extensions` package with extension hook events, a `memorix` command, official skills, and writes MCP config.

Need a quieter install? Add `--noHooks` for targets where setup can control hook capture separately from the host's official package entry.

If you intentionally want repo-local guidance or hooks, run the same command inside that repository without `--global`.

If your agent only needs a manual MCP entry, use stdio:

```json
{
"mcpServers": {
"memorix": {
"command": "memorix",
"args": ["serve"]
}
}
}
```

HTTP is not required for normal setup. Use it only when you intentionally want a shared background service, dashboard, Docker, or multiple clients using the same endpoint:

```bash
memorix background start
```

Then point the client at:

```text
http://localhost:3211/mcp
```

In HTTP mode, agents should bind the active repo explicitly with `memorix_session_start(projectRoot=...)` when the client can provide the workspace path. Git remains the final source of truth for project identity.

### Uninstall

Preview what will be removed:

```bash
memorix uninstall --dry-run
```

Stop the background service and remove hooks:

```bash
memorix uninstall --background --hooks
```

Full cleanup:

```bash
memorix uninstall --yes --background --hooks --purge-data
npm uninstall -g memorix
```

`memorix uninstall` reports MCP config entries for manual cleanup instead of silently editing every MCP file it finds.

### Work from the CLI

```bash
memorix context --task "continue release blocker"
memorix memory search --query "release blocker"
memorix reasoning search --query "why sqlite"
memorix git-hook --force
memorix ingest log --count 20
memorix dashboard
```

### Use the bundled terminal agent

```bash
memorix
# or
memcode
```

This opens memcode, a terminal coding agent that uses the same Memorix project memory as your MCP-connected agents.

| Layer | Stores | Best for |
| --- | --- | --- |
| Observation Memory | facts, gotchas, fixes, implementation notes | "How does this work?" |
| Reasoning Memory | rationale, alternatives, constraints, risks | "Why did we choose this?" |
| Git Memory | commit-derived engineering facts | "What changed and where?" |
| Code Memory | files, symbols, import edges, and memory-to-code freshness | "Which current code should I inspect first?" |

Search is project-scoped by default. `scope="global"` searches across projects. The search boosts Git Memory for "what changed" questions and reasoning records for "why" questions.

`memorix context --task "..."` is the default Memory Autopilot entry. It builds a compact task-lensed brief for agents: bugfix tasks lean toward tests and repros, release tasks lean toward package/changelog/build checks, onboarding tasks lean toward docs and entry points, and stale or unrelated memories stay in warning lanes instead of flooding the prompt. Agents should read the suggested files before trusting stored memory.

| You want | Run |
| --- | --- |
| Install an agent integration package | `memorix setup --agent --global` |
| Check or repair an agent integration | `memorix doctor agents --agent `, `memorix repair agents --agent ` |
| Manually expose stdio MCP | `memorix serve` |
| Run shared HTTP MCP plus dashboard | `memorix background start` |
| Debug HTTP MCP in the foreground | `memorix serve-http --port 3211` |
| Inspect or manage memory directly | `memorix memory`, `memorix reasoning`, `memorix session`, `memorix ingest` |
| Use the bundled terminal agent | `memorix` or `memcode` |
| Run orchestrated subagent work | `memorix orchestrate --goal "..."` |

`memorix serve` defaults to `--mode micro` (7 tools) to keep MCP tool schemas small for agents. Use `--mode lite` for the extended solo memory surface, `--mode team` for coordination tools, or `--mode full` for advanced and compatibility tools.

`memorix orchestrate` uses the current checkout for single-worker runs. When running multiple workers, it creates task worktrees under `.worktrees/` and merges successful task branches back. Use `--isolated` to force worktree isolation for one worker, `--no-worktree` to disable it, `--allow-dirty` to run with uncommitted changes, and `--no-auto-merge` to preserve task worktrees for manual review.

memcode is the terminal coding agent bundled with Memorix. It can read, edit, run commands, resume sessions, switch models, and use `/memory` commands — all backed by the same project memory as your MCP-connected agents.

Use it when you want a terminal agent with memory already wired in.

```text
one Git project -> one shared Memorix memory pool
```

See [docs/MEMCODE.md](docs/MEMCODE.md) for the memcode-specific guide.

Minimal `~/.memorix/config.toml`:

```toml
[agent]
provider = "openai"
model = "gpt-4o"
api_key = "..."

[memory.llm]
provider = "openai"
model = "gpt-4o-mini"
api_key = "..."

[embedding]
provider = "auto"

[memory]
inject = "minimal"
formation = "active"
```

Use `[memory.llm]` and `[embedding]` for Memorix memory quality and retrieval. Use `[agent]` for the model memcode talks to while coding. Keep credentials in global config or environment variables, and do not commit secrets.

For OpenRouter embeddings, use `provider = "api"`, `base_url = "https://openrouter.ai/api/v1"`, and `model = "qwen/qwen3-embedding-8b"`. Memorix accepts `OPENROUTER_API_KEY` for that embedding endpoint; `MEMORIX_EMBEDDING_API_KEY` remains the explicit override.

Docker is for the HTTP service, not stdio MCP:

```bash
docker compose up --build -d
```

Then open:

- dashboard: `http://localhost:3211`
- MCP: `http://localhost:3211/mcp`
- health: `http://localhost:3211/health`

The container must be able to access the repository path passed as `projectRoot` for project-scoped Git and config behavior.

Use Memorix directly from TypeScript:

```ts
import { createMemoryClient } from 'memorix/sdk';

const client = await createMemoryClient({ projectRoot: '/path/to/repo' });

await client.store({
entityName: 'auth-module',
type: 'decision',
title: 'Use JWT for API auth',
narrative: 'Chose JWT because the API is stateless and used by multiple clients.',
});

const results = await client.search({ query: 'auth decision' });
await client.close();
```

| Start here | Use when |
| --- | --- |
| [Docs Map](docs/README.md) | You want the shortest route to the right guide |
| [Setup Guide](docs/SETUP.md) | Installing, using `memorix setup`, choosing stdio vs HTTP |
| [Integration Surfaces](docs/INTEGRATIONS.md) | Plugin packages, MCP, project rules, hooks, and skills support |
| [Configuration](docs/CONFIGURATION.md) | TOML config, model lanes, compatibility files |
| [API Reference](docs/API_REFERENCE.md) | MCP tools and CLI commands |
| [Git Memory](docs/GIT_MEMORY.md) | Commit ingestion and searchable engineering truth |
| [Docker](docs/DOCKER.md) | Containerized HTTP service |
| [memcode](docs/MEMCODE.md) | Using the bundled terminal agent |
| [Agent Playbook](docs/AGENT_OPERATOR_PLAYBOOK.md) | AI-facing execution guide for install, binding, hooks, and troubleshooting |
| [Development](docs/DEVELOPMENT.md) | Contributing, testing, release checks |
| [Changelog](CHANGELOG.md) | What changed in each release |

LLM-friendly summaries: [llms.txt](llms.txt) and [llms-full.txt](llms-full.txt).

```bash
git clone https://github.com/AVIDS2/memorix.git
cd memorix
npm install
npm run lint
npm test
npm run build
```

Memorix draws from the MCP ecosystem and prior memory projects such as mcp-memory-service, MemCP, claude-mem, and Mem0. memcode is based on the Pi coding-agent codebase and adapts its terminal-agent model for the Memorix ecosystem.

[Apache 2.0](LICENSE)

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Awesome

https://github.com/AVIDS2/memorix

Awesome Lists containing this project

README

Memorix