Agents Memory Sidecar
FreeMaintainedLocal-first shared memory sidecar for MCP-capable AI agents.
About
Local-first shared memory sidecar for MCP-capable AI agents.
README
Local-first shared memory for MCP-capable AI agents.
Breaking change in 0.4.0: token registry files now store SHA-256 hex digests of bearer tokens as keys — plaintext tokens are rejected at startup. Convert an existing file with
node scripts/migrate-http-tokens.mjs --file <path>, or generate fresh tokens withscripts/upsert-http-token.mjs. See the CHANGELOG for details.
Agents Memory Sidecar lets tools such as Codex, Claude Code, Grok, agy, Pi, and other MCP clients share operational memory through one local sidecar. It is designed for coding agents that need to search prior context before changing a project and store durable non-secret facts after work is validated.
Agent CLI -> stdio MCP wrapper -> localhost HTTP sidecar -> PostgreSQL + pgvector
The HTTP server is intended to listen on 127.0.0.1 only. Do not expose it directly to the public internet.
Features
- MCP tools for searching, reading, and writing shared memory
- Project context storage for stable paths, services, ports, and conventions
- Short-lived agent observations with TTL
- HTTP sidecar with bearer-token authentication
- Actor identity derived from token registry, not model-provided fields
- PostgreSQL persistence with pgvector-backed semantic and hybrid search
- Secret rejection for common token/private-key patterns
- Audit events for writes, permission denials, unauthorized calls, and pruning
- Fake JSON store for local development and smoke tests
MCP Tools
memory_searchmemory_getproject_context_getmemory_addagent_observation_addproject_context_set(admin-only)
Search Modes
Search defaults to keyword/full-text mode. PostgreSQL deployments can enable semantic or hybrid mode after backfilling memory_embeddings; see Configuration and Semantic And Hybrid Search.
Guides
- Architecture
- 5-Minute Demo Transcript
- PostgreSQL Quickstart
- Docker Compose Quickstart
- 30-Minute Durable Deployment Transcript
- Semantic And Hybrid Search
- Search Benchmark
- Memory Governance
- Agent Integrations
- Operations
- Backup And Restore
- Security Model
- Release Checklist
- Support Matrix
- Good First Issues
- v0.2.1 Release Evidence
- v0.3.1 Release Evidence
- v0.3.0 CI Evidence
- v0.3.0 Construction Plan
- v0.3.2 P0 Task List
Quick Start
Install From Source
git clone https://github.com/zenbordercom/agents-memory-sidecar.git
cd agents-memory-sidecar
npm install
npm run build
Validate the checkout and build output:
node scripts/check-installation.mjs --profile quickstart --pretty
Demo Mode
Demo mode uses the fake JSON store and does not require PostgreSQL, systemd, or production config files:
npm run smoke
npm run http:smoke
npm run http:bridge-smoke
Use the fallback CLI against the fake store:
AGENT_MEMORY_AGENT_ID=local-cli \
AGENT_MEMORY_RUNTIME=local \
AGENT_MEMORY_ROLE=writer \
AGENT_MEMORY_PROJECTS='*' \
node dist/cli.js memory_add '{
"tenant":"default",
"project":"demo-app",
"namespace":"ops",
"kind":"note",
"title":"Demo memory",
"body":"Agents Memory Sidecar demo mode is running with the fake store.",
"source_type":"manual"
}'
Search it:
AGENT_MEMORY_AGENT_ID=local-cli \
AGENT_MEMORY_RUNTIME=local \
AGENT_MEMORY_ROLE=writer \
AGENT_MEMORY_PROJECTS='*' \
node dist/cli.js memory_search '{
"tenant":"default",
"project":"demo-app",
"query":"demo mode",
"limit":5
}'
Local HTTP Sidecar Mode
HTTP authentication fails closed. agents-memory-http will not listen unless a
valid token registry is configured (AGENT_MEMORY_HTTP_TOKENS_FILE or
AGENT_MEMORY_HTTP_TOKENS_JSON). For deliberate loopback demos only, set
AGENT_MEMORY_ALLOW_UNAUTHENTICATED_LOCAL=1 with a loopback bind host.
GET /healthz stays unauthenticated for local liveness checks.
Create a private local token registry. Generate the bearer token yourself and pass it to the upsert helper — the registry stores only its SHA-256 digest:
mkdir -p .local/agents-memory
export AGENT_MEMORY_HTTP_BEARER_TOKEN="$(node -e "console.log(require('node:crypto').randomBytes(32).toString('base64url'))")"
node scripts/upsert-http-token.mjs \
--file .local/agents-memory/http-tokens.json \
--token "$AGENT_MEMORY_HTTP_BEARER_TOKEN" \
--agent-id local-cli \
--runtime local \
--role writer \
--projects '*'
The upsert script prints a fingerprint only and never echoes the token. Keep
AGENT_MEMORY_HTTP_BEARER_TOKEN exported in whichever shell calls the CLI
below.
Start the HTTP sidecar in one terminal:
AGENT_MEMORY_HTTP_TOKENS_FILE="$PWD/.local/agents-memory/http-tokens.json" \
AGENT_MEMORY_HTTP_HOST=127.0.0.1 \
AGENT_MEMORY_HTTP_PORT=18790 \
npm run http:dev
In another terminal, call it through the CLI HTTP backend (re-export
AGENT_MEMORY_HTTP_BEARER_TOKEN with the value you generated above if you
opened a new shell):
AGENT_MEMORY_BACKEND=http \
AGENT_MEMORY_HTTP_BASE_URL=http://127.0.0.1:18790 \
AGENT_MEMORY_AGENT_ID=local-cli \
AGENT_MEMORY_RUNTIME=local \
AGENT_MEMORY_ROLE=writer \
AGENT_MEMORY_PROJECTS='*' \
node dist/cli.js memory_add '{
"tenant":"default",
"project":"demo-app",
"namespace":"ops",
"kind":"note",
"title":"HTTP sidecar demo",
"body":"The local HTTP sidecar accepts bearer-token memory writes.",
"source_type":"manual"
}'
Search it:
AGENT_MEMORY_BACKEND=http \
AGENT_MEMORY_HTTP_BASE_URL=http://127.0.0.1:18790 \
AGENT_MEMORY_AGENT_ID=local-cli \
AGENT_MEMORY_RUNTIME=local \
AGENT_MEMORY_ROLE=writer \
AGENT_MEMORY_PROJECTS='*' \
node dist/cli.js memory_search '{
"tenant":"default",
"project":"demo-app",
"query":"HTTP sidecar",
"limit":5
}'
Durable PostgreSQL Mode
Use PostgreSQL when you want durable shared memory:
AGENT_MEMORY_BACKEND=postgres \
PGDATABASE=agent_memory \
npm run db:migrate
Then run the PostgreSQL smoke test:
npm run postgres:smoke
See PostgreSQL Quickstart for a complete local database setup.
Installation Options
Install the current npm release:
npm install -g [email protected]
Verify the registry version and dist-tag:
npm view agents-memory-sidecar version
npm view agents-memory-sidecar dist-tags.latest
Both commands should print 0.3.1.
You can also install the matching GitHub release tag:
npm install -g github:zenbordercom/agents-memory-sidecar#v0.3.1
Or install the GitHub release tarball:
npm install -g https://github.com/zenbordercom/agents-memory-sidecar/releases/download/v0.3.1/agents-memory-sidecar-0.3.1.tgz
The CLI entry points are:
agents-memory --help
agents-memory-mcp
agents-memory-http
agents-memory: JSON CLI for direct commands and fallback automation.agents-memory-mcp: stdio MCP wrapper for agent clients.agents-memory-http: local HTTP sidecar.
Quick Start Troubleshooting
- Missing
dist/*.js: runnpm run build. - Missing token registry / startup refused: create a registry with
scripts/upsert-http-token.mjs, setAGENT_MEMORY_HTTP_TOKENS_FILE, and restart. Tokenless mode requiresAGENT_MEMORY_ALLOW_UNAUTHENTICATED_LOCAL=1on loopback only. - HTTP connection refused: start
agents-memory-httpornpm run http:dev, then runnode scripts/check-installation.mjs --profile quickstart --check-http --expected-backend fake --pretty. unauthorized: sendAuthorization: Bearer <token>from the registry.permission_denied: check that the bearer token actor has the required role and project access.
Agent Setup
The recommended client pattern is:
- Store the bearer token in a private env file.
- Create a small launcher script that sources that env file.
- Point the agent's MCP config at the launcher.
See Agent Integrations and integrations/*/README.md.
Security Defaults
- Bind the HTTP sidecar to
127.0.0.1. - Require a token registry; do not rely on fail-open environment actor fallback.
- Keep full bearer tokens out of Git, chat, logs, and docs.
- Use separate tokens per agent.
- Give normal agents
writer, notadmin. - Store stable facts, not secrets or raw
.envfiles. - Treat model-provided actor fields as untrusted.
See Security Model.
Production Operations
Optional scripts and systemd unit examples are included for local Linux deployments. Review paths, users, groups, database roles, and backup passphrase handling before use.
sudo scripts/install-local.sh
See Operations and Backup And Restore.
Limitations
- Search defaults to keyword/full-text mode. Semantic and hybrid search require stored embeddings and an embedding model or explicit query embedding.
- The project does not replace an agent's internal conversation memory.
- The sidecar is local-first and not designed as a public multi-tenant SaaS API.
- Fresh install automation is intentionally minimal in this version.
What This Is Not
- Not a hosted SaaS API or public internet service.
- Not an agent scheduler or orchestration framework.
- Not a secret manager.
- Not full conversation memory.
- Not a replacement for each agent's native session state.
License
Apache-2.0.
Install Agents Memory Sidecar in Claude Desktop, Claude Code & Cursor
unyly install agents-memory-sidecarInstalls into Claude Desktop, Claude Code, Cursor & VS Code — handles npx, uvx and build-from-source repos for you.
First time? Get the CLI: curl -fsSL https://unyly.org/install | sh
Or configure manually
Run in your terminal:
claude mcp add agents-memory-sidecar --env AGENT_MEMORY_AGENT_ID="" --env AGENT_MEMORY_BACKEND="" --env AGENT_MEMORY_HTTP_BASE_URL="" --env AGENT_MEMORY_HTTP_BEARER_TOKEN="" --env AGENT_MEMORY_HTTP_HOST="" --env AGENT_MEMORY_HTTP_PORT="" --env AGENT_MEMORY_HTTP_TOKENS_FILE="" --env AGENT_MEMORY_PROJECTS="" --env AGENT_MEMORY_ROLE="" --env AGENT_MEMORY_RUNTIME="" --env PGDATABASE="" -- npx -y agents-memory-sidecarStep-by-step: how to install Agents Memory Sidecar
FAQ
Is Agents Memory Sidecar MCP free?
Yes, Agents Memory Sidecar MCP is free — one-click install via Unyly at no cost.
Does Agents Memory Sidecar need an API key?
Yes, it requires environment variables: AGENT_MEMORY_AGENT_ID, AGENT_MEMORY_BACKEND, AGENT_MEMORY_HTTP_BASE_URL, AGENT_MEMORY_HTTP_BEARER_TOKEN, AGENT_MEMORY_HTTP_HOST, AGENT_MEMORY_HTTP_PORT, AGENT_MEMORY_HTTP_TOKENS_FILE, AGENT_MEMORY_PROJECTS, AGENT_MEMORY_ROLE, AGENT_MEMORY_RUNTIME, PGDATABASE. Unyly injects them into the config during install.
Is Agents Memory Sidecar hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install Agents Memory Sidecar in Claude Desktop, Claude Code or Cursor?
Open Agents Memory Sidecar on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Fetch
Web content fetching and conversion for efficient LLM usage.
Roblox Studio
Enables AI coding tools to control Roblox Studio for workspace exploration, instance manipulation, and script management. It provides tools for playtesting, sce
by paralovAWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
by xuzexin-hzMCP-Agent
A simple, composable framework to build agents using Model Context Protocol by [LastMile AI](https://www.lastmileai.dev)
by lastmile-aiSpring AI MCP Client
Provides auto-configuration for MCP client functionality in Spring Boot applications.
mcp.natoma.ai
A Hosted MCP Platform to discover, install, manage and deploy MCP servers by [Natoma Labs](https://www.natoma.ai)
MCPHub
Website to list high quality MCP servers and reviews by real users. Also provide online chatbot for popular LLM models with MCP server support.
MCP Servers Rating and User Reviews
Website to rate MCP servers, write authentic user reviews, and [search engine for agent & mcp](http://www.deepnlp.org/search/agent)
Compare Agents Memory Sidecar with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs
