Gives AI coding agents a shared, searchable project memory that persists across chats, IDEs, and tools.
Also known as AVIDS2/memorix
- Stars
- 935
- Tools
- 9
- Downloads, 30 days
- —
- Latest version
- 1.10.2
- Last commit
- Nov 11, 2026
- License
- Apache-2.0
What is Memorix MCP?
Memorix gives AI coding agents a shared, searchable project memory that persists across chats, IDEs, and tools. It exposes 9 tools, such as memorix_store, memorix_search, memorix_project_context.
Summary generated from the project's README
About Memorix MCP server
Providing AI coding agents with a persistent, searchable project memory is what Memorix accomplishes. It creates a local-first memory layer that lives within your Git project, ensuring that knowledge gained in one session or tool is available to others. This allows developers to switch between different environments like Cursor, Windsurf, or Claude Code without losing the context of previous design decisions or technical fixes.
Users can integrate this system into their workflow using MCP, CLI commands, or the bundled memcode terminal agent. The memory is stored locally using SQLite, with options for Orama or LanceDB for indexing. It features specialized capabilities like Git Memory to turn commits into engineering facts and Reasoning Memory to preserve the rationale behind architectural choices. This setup ensures that even when you change agents or IDEs, the project intelligence remains consistent and accessible through a unified local control plane.
What you can do with it
- 1Preserving design rationaleAsk the agent to recall why a specific architectural choice was made during a previous session.
- 2Syncing context across toolsMaintain a single pool of project knowledge when moving from a terminal agent to a different IDE.
- 3Converting history to factsInstruct the agent to analyze recent code changes to understand the project's current state.
- 4Coordinating multi-agent tasksUse the orchestration feature to manage handoffs and verification loops between different workers.
Written from the project's README. Every use case is checked against a quote from it.
How to install Memorix MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Memorix MCP in Claude Code
$ claude mcp add memorix -- npx -y memorix serveInstall Memorix MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"memorix": {
"command": "npx",
"args": [
"-y",
"memorix",
"serve"
]
}
}
}Install Memorix MCP in VS Code
.vscode/mcp.json
{
"servers": {
"memorix": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"memorix",
"serve"
]
}
}
}Install Memorix MCP in VS Code CLI
$ code --add-mcp '{"name":"memorix","type":"stdio","command":"npx","args":["-y","memorix","serve"]}'Install Memorix MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"memorix": {
"command": "npx",
"args": [
"-y",
"memorix",
"serve"
]
}
}
}Install Memorix MCP in Codex
$ codex mcp add memorix -- npx -y memorix serveInstall Memorix MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.memorix] command = "npx" args = ["-y", "memorix", "serve"]
Install Memorix MCP in Gemini CLI
$ gemini mcp add -s user memorix npx -- -y memorix serveInstall Memorix MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"memorix": {
"command": "npx",
"args": [
"-y",
"memorix",
"serve"
]
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for memorix 1.10.2 in an isolated container with no network and no keys. It answered and listed 9 tools.
Memorix MCP tools 9
Read from the server with tools/listmemorix_storeStore a new observation/memory. Automatically indexed for search. Use type to classify: gotcha ([GOTCHA] critical pitfall), decision ([DECISION] architecture choice), problem-solution ([FIX] bug fix), how-it-works ([INFO] explanation), what-changed ([CHANGE] change), discovery ([DISCOVERY] insight), why-it-exists ([WHY] rationale), trade-off ([TRADEOFF] compromise), session-request ([SESSION] original goal). Project visibility is the default. Personal or team visibility requires an explicitly joined coordination identity. Set longTerm only when the caller explicitly wants an additional source-backed long-term candidate; it is never injected until an operator records a review through the CLI. For a read-only task, do not store unless the user explicitly asks to save a record.
memorix_searchSearch project memory. Returns a compact index (~50-100 tokens/result). Do not use as a follow-up to a complete memorix_project_context brief unless a specific fact is still missing or the user asks for deeper history; provide purpose when intentionally expanding. Use memorix_detail to fetch full content for specific IDs. Use memorix_timeline to see chronological context. Searches across all observations stored from any IDE session — enabling cross-session and cross-agent context retrieval.
memorix_project_contextBuild a compact Memory Autopilot brief for the current coding task. Schedules Code Memory refresh when needed, includes Start here files, reliable code-bound memories, stale/suspect cautions, and verification hints. Use this at the start of a new coding turn or after switching tasks.
memorix_codegraph_statusShow CodeGraph Memory provider and index status for the current project.
memorix_context_packBuild a prompt-ready working context pack for a coding task. Combines relevant memories, CodeGraph Memory facts, freshness warnings, suggested reads, and verification hints. After a complete memorix_project_context brief, provide purpose only when deliberately expanding beyond it.
memorix_resolveMark observations as resolved (completed/no longer active). Resolved memories are hidden from default search but can still be found with status="all". Use this to mark completed tasks, fixed bugs, or outdated information so they don't pollute future context.
memorix_detailFetch full observation, mini-skill, or curated durable-memory details — includes source kind (explicit memory / hook trace / git evidence), value category, and cross-references (~500-1000 tokens each). Do not re-fetch content already covered by a complete memorix_project_context brief unless a specific fact is still missing or the user asks for deeper history; provide purpose when intentionally expanding. Always use memorix_search first to find relevant IDs, then fetch only what you need. Accepts typed refs from search results (e.g. "obs:42", "skill:3") and durable refs from a project brief (e.g. "durable:<uuid>") via the typedRefs field, or legacy numeric ids / object refs for backward compatibility.
memorix_session_startStart a new coding session. Returns a compact continuation card with the latest handoff and a few memory references. Call this at the beginning of a session to track activity; retrieve a referenced memory only when it is relevant. Any previous active session for this project will be auto-closed. By default this is lightweight: it binds the project, opens a session, and avoids dumping full history into the new context. Coordination identity is opt-in via `joinTeam: true` or a separate `team_manage` join call. IMPORTANT for HTTP/control-plane mode: pass `projectRoot` with the absolute path to your workspace root (e.g., the directory open in your IDE). Memorix uses this to detect the git project and bind this session to the correct project context. Without it, project-scoped tools will be disabled.
memorix_mediaUse the controlled local media library for an explicit import, attachment, inspection, or MiniMax generation request. Assets stay outside the Git worktree and enter normal memory only when attach is explicitly true. Use the CLI for destructive removal, quota cleanup, and direct generation. MCP generation is disabled by default and requires MEMORIX_MCP_MEDIA_GENERATION=1 after the operator reviews provider billing.
Automated checks
Ran Nov 16, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachableavids2/memorix is public and reachablegithub.com/avids2/memorix ↗Pass
- Package names this repository as its sourcememorix names avids2/memorix as sourcenpmjs.com/package/memorix ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for memorixnpmjs.com/package/memorix/v/1.10.2#provenance ↗Pass
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-11github.com/avids2/memorix ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from memorixPass
- No critical advisory in the package or its dependencies320 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model9 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubMaintainer status and the current public work boundary live in ACTIVE_WORK.md. It is the repository's single living work tracker.
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. Small projects use the in-process Orama path; larger projects use a persistent SQLite FTS5 candidate index and, when available, an optional local LanceDB semantic shadow index. Both indexes are rebuildable and are never a limit on how many durable memories you can keep. LLM-backed formation and embedding remain optional.
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 bounded task Workset with start files, current memory, source-backed knowledge, workflow starts, cautions, and verification. Compact JSON receipts keep fallback CLI use bounded too. | memorix context "..." --brief-json, memorix resume "..." --brief-json, 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 |
| Curated Long-term Memory | Deliberately reviewed episodic, semantic, and procedural memory with source evidence. Only an explicitly portable user item can cross local projects | memorix memory long-term |
| Code State and Code Memory | Versioned local code snapshots, source-backed TypeScript/JavaScript symbols and relations, file/symbol links, and freshness checks. Other languages keep the honest Lite fallback; an already-indexed local CodeGraph or SCIP result can add a bounded external outline without taking over the local index. | memorix codegraph status|refresh|init|sync, 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 |
| Knowledge Workspace | Review-gated source-backed claims, Markdown pages, and canonical project workflows; proposals never overwrite reviewed pages silently | memorix knowledge, memorix knowledge workflow |
| Agent setup | One setup path for MCP, rules, hooks, skills, plugins, bundles, or extensions depending on the agent | memorix setup --agent <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, diagnostics, and preview-first cleanup, consolidation, deduplication, and retention actions | 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() |
| Optional multi-device sync | Privacy-filtered observation events with local SQLite kept canonical; default project scope, optional --scope user for every local project; GitHub JSONL, filesystem, S3, or Postgres relay |
memorix sync store status|push|pull |
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.
Integration surfaces:
| Surface | What it does | Memorix entry |
|---|---|---|
| Setup command | Installs the recommended one-time user-level Memorix integration | memorix setup --agent <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 capture of prompts, tool events, file edits, session lifecycle events, and native compaction checkpoints where the agent exposes them | 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, CodeBuddy Code, 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, DeepSeek Harness, WorkBuddy |
| 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 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:
memorixCLI is the direct command surface for setup, memory search/store, Git Memory, import/export, dashboard, orchestration, diagnostics, and automation.memorix serveis the stdio MCP bridge used by IDEs and coding agents. Its default tool profile ismicro, so agents see only the compact core tool set.memorix background start/memorix serve-httprun the HTTP service for a shared endpoint, dashboard, VPS Docker deployment, or multiple clients.
Multi-device store sync is opt-in and separate from HTTP sharing. It never
uploads the live SQLite database or WAL files. By default it only relays
qualified project-visible observations for the current Git project; personal,
agent-targeted, candidate, and ephemeral records stay local. Pass --scope user
to include every local project. Set MEMORIX_SYNC_PROVIDER and inspect
memorix sync store status --json before the first push.
Requirements:
- Node.js
>=22.18.0 - Git, because project identity is derived from the real Git root
Install and initialize:
npm install -g memorix
memorix init --global # optional defaults
memorix setup --agent claude --global # or codex, copilot, cursor, pi, gemini-cli, opencode,
# codebuddy, windsurf, kiro, antigravity, trae, openclaw, hermes, omp
memorix init is optional. It creates or updates TOML configuration:
~/.memorix/config.tomlfor global defaults<git-root>/memorix.tomlfor 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. Codex is the exception: its supported path is the user-level plugin install, so Memorix leaves project .codex configuration alone.
Connect an existing agent
Use the setup command first. The global form is the normal one-time install:
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 codebuddy --global
memorix setup --agent omp --global
memorix setup --agent dsh --global
memorix setup --agent workbuddy --global
memorix setup --agent grok --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.mdguidance, and enables hook capture when you do not pass--noHooks. - Codex: installs one user-level Memorix plugin with bundled stdio MCP, skills, and lifecycle hooks. It does not write project-local
.codexconfig or change your model, approval, or sandbox settings. When Codex asks, review the plugin hook definition once with/hooks;--noHooksskips automatic capture. - GitHub Copilot CLI: installs the Copilot plugin package and official Memorix skills.
- Pi: installs the Pi extension/skills package and native MCP config (Pi 1.0+):
~/.pi/agent/mcp.jsonwith--global, or.pi/mcp.jsonfor project setup. - Cursor: writes Cursor MCP/rules/config entries in the chosen scope.
- Gemini CLI: installs the extension package,
GEMINI.mdcontext, 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, andAGENTS.mdguidance. - 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/memorixor.agents/plugins/memorix. - OpenClaw: installs an OpenClaw-compatible bundle with
.mcp.json, official skills, and an OpenClawHOOK.md/handler.tshook pack. - Hermes Agent: installs into Hermes home (
%LOCALAPPDATA%\hermeson native Windows,~/.hermeselsewhere, orHERMES_HOME), enables the plugin inconfig.yaml, registers plugin hooks, slash/CLI commands, skills, and writes MCP config. - CodeBuddy Code: installs a user-scope local marketplace plugin under
~/.codebuddy/memorix-localwith MCP, skills, and hooks. It does not change existing CodeBuddy model, permission, or settings files; CodeBuddy keeps third-party hook approval in its own/hooksflow. - Oh-my-Pi: installs an
omp.extensionspackage with extension hook events, amemorixcommand, official skills, and writes MCP config. - DeepSeek Harness: writes a Memorix
@deepseek-ai/dsh-mcp-clientrow into$DSH_HOME/cordis.patch.yml(default~/.dsh/cordis.patch.yml), appends guidance to the harnessAGENTS.md, and installs official skills under$DSH_HOME/skills. The row follows DSH's own shipped Memorix reference, so tools appear asmcp__memorix__*. - WorkBuddy: writes a Memorix MCP server row into
~/.workbuddy/mcp.json(or<project>/.workbuddy/mcp.jsonfor project installs) and appends guidance toAGENTS.md. Tools appear asmcp__memorix__*; there is no hooks surface. - Grok Build: installs native lifecycle hooks under
~/.grok/hooks/memorix.jsonand guidance in~/.grok/AGENTS.md. MCP stays host-owned by default; pass--mcp httpto write[mcp_servers.memorix]withurl = "http://localhost:3211/mcp". Project-local hooks require Grok/hooks-trust, while global hooks are trusted. SetGROK_HOMEto use a custom Grok home.
Need a quieter install? Add --noHooks for targets where setup can control hook capture separately from the host's official package entry. It keeps MCP and guidance, but skips Memorix hook capture.
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:
{
"mcpServers": {
"memorix": {
"command": "memorix",
"args": ["serve"]
}
}
}
For an npm-based MCP client or registry tester, use the complete command
npx -y memorix serve. The serve argument matters: memorix without
arguments opens the bundled memcode terminal agent when run by a human, while
MCP clients should start the stdio server explicitly.
For a manually managed Claude Code entry, add "alwaysLoad": true inside the memorix server object. This lets Claude Code expose Memorix tools during print-mode startup; memorix doctor agents --agent claude can detect and repair a missing setting.
HTTP is not required for normal setup. Use it only when you intentionally want a shared background service, dashboard, VPS Docker deployment, or multiple clients using the same endpoint. Local development uses the Node service directly and does not require Docker:
memorix background start
Then point the client at:
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.
Memorix MCP questions
How do I add Memorix MCP to Claude Code?
Run claude mcp add memorix -- npx -y memorix serve in your terminal. Add --scope user to make it available in every project.
How do I add Memorix MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Memorix MCP provide?
It exposes 9 tools, including memorix_store, memorix_search, memorix_project_context, memorix_codegraph_status, memorix_context_pack.
What is Memorix?
Memorix is a local-first shared memory layer that gives AI coding agents a searchable project memory surviving new chats, IDE switches, and handoffs.
Where does Memorix store memory?
SQLite is the canonical store, with an in-process Orama index for small projects and optional LanceDB semantic index for larger ones.
Which agents does Memorix work with?
It connects to agents like Claude Code, Codex, Cursor, Windsurf, Copilot, and Gemini CLI through plugins, MCP, rules, hooks, or skills.
What is Git Memory in Memorix?
Git Memory turns commits into searchable engineering facts that answer what changed, where, and why it matters.