Remembra Relay

One agent stops. The next one already knows.
When an agent's session ends, Remembra Relay saves a handoff built from what git says happened.
The next agent, on another machine, from another vendor, or next week, starts from it.

Website • Relay guide • Docs • Changelog • Discord

Install

First get a free key at app.remembra.dev, then run:

pipx install --force 'remembra[mcp]>=0.16'
remembra-install --all
remembra-relay connect --apply

remembra-install asks for the key at a hidden prompt (or reads REMEMBRA_API_KEY) and shows its changes before it writes. connect --apply writes the hooks and keeps a backup of each file; run remembra-relay connect alone first to see every change without writing. Codex runs the hooks only after you trust them: run /hooks in Codex once. Hosting the server yourself? Add --url <your server> to remembra-install. remembra-relay ships in remembra 0.16.0.

Handoffs not arriving? remembra-relay doctor says where the baton dropped, from this machine's files and your trail, with one fix per problem; it only reads. Inside your agent the local MCP server has the same checks as read-only tools: remembra_doctor, remembra_setup (the install steps for this machine) and remembra_help. See Doctor.

What the next agent sees

Claude Code finished a session and wrote in its summary that the work was done and pushed. Git disagreed. The next agent's brief starts with:

Last session: claude-code (key-verified), 12m ago, on feat/pdf-export@a41f2c9: done: a41f2c9 Add PDF export for invoices; 77c01aa Embed fonts in exported PDFs; tests passing: pytest tests/test_pdf.py (12 passed); changed 3 file(s): invoices/pdf.py, invoices/fonts.py, tests/test_pdf.py / NOT done: 2 commit(s) not pushed to origin/feat/pdf-export / failing: none / next (derived from the recorded facts): push 2 commit(s) to origin/feat/pdf-export (facts collected by remembra-relay from git and the session transcript) (the agent's summary contradicts these recorded facts)

The done, not done and failing sections come from git and the session's test runs, never from an LLM. The agent's own summary is optional; it is checked against those facts and shown as unverified, or, as here, contradicted.

How it works

1. Close. When a session ends, remembra-relay close reads the branch, commits, changed and uncommitted files and unpushed commits from git, and, for Claude Code and Codex, the commands, test runs and open items in the local transcript (Codex's is its rollout file). The transcript never leaves your machine; secrets are redacted before anything does.
2. Brief. When the next session starts, in the same tool or another, remembra-relay brief (run by the verified session hooks) or the session_brief MCP tool (any MCP agent can call it) gives the agent who worked last, what is done, what is failing and the next step, in about 1,500 tokens. Everything another agent recorded is wrapped as untrusted data.
3. Trail. Every handoff stays in order: remembra-relay trail, or the Trail page in the dashboard. A git log for your agents.

The same repository on a laptop, a server or in a worktree is one project, because it is identified by its git remote. Give each agent its own scoped key and its handoffs show as key-verified.

Agents

Claude Code's and Codex's session hooks are verified (Codex with codex-cli 0.155.0-alpha.16.4, a prerelease; no stable Codex release has been run yet). The Gemini CLI, Qwen Code and Kimi Code hooks are verified too: each was run against the real tool at the version in the table, with a local stand-in for the model, and put the brief in the model's request and posted the handoff; other versions have not been run. The Cursor hooks are unverified: Cursor's own hook runner ran them, but no logged-in Cursor session has yet. connect leaves them out unless you add --include-unverified. Until they are tested, Cursor reads the brief and writes its handoff through Remembra's MCP tools, as does any MCP agent.

How it compares

Details, with a source and date for every claim: Remembra and other handoff tools. claude-mem and agentmemory are larger projects that also carry memory between sessions; the comparison says where each is the better pick.

Pricing

Handoffs, briefs, the inbox, the trail and search are free on every plan. Remembra Cloud: Free, Solo $12/mo, Pro $29/mo, Team $15/seat/mo (pricing). Self-hosting is free under the MIT license.

The memory API underneath

Remembra Relay runs on Remembra's memory layer, which you can also use directly: store facts, recall them by meaning, and let it pull out the people, projects and relationships in them.

from remembra import Memory

memory = Memory(user_id="user_123")
memory.store("Had a meeting with Sarah from Acme Corp. She prefers email over Slack.")
result = memory.recall("How should I contact Sarah?")
print(result.context)
# "Sarah from Acme Corp prefers email over Slack."

In v0.16.0 the memory layer also keeps the exact source text of every derived fact, points each fact back to it, and flags a fact that does not match its source as unverified.

Self-host the server (2 minutes)

One Command Install

curl -sSL https://raw.githubusercontent.com/remembra-ai/remembra/main/quickstart.sh | bash

That's it. Remembra + Qdrant + Ollama start locally. No API keys needed.

Or with Docker Compose directly:

git clone https://github.com/remembra-ai/remembra && cd remembra
docker compose -f docker-compose.quickstart.yml up -d

Try it:

# Store a memory
curl -X POST http://localhost:8787/api/v1/memories \
  -H "Content-Type: application/json" \
  -d '{"content": "Alice is CEO of Acme Corp", "user_id": "demo"}'

# Recall it
curl -X POST http://localhost:8787/api/v1/memories/recall \
  -H "Content-Type: application/json" \
  -d '{"query": "Who runs Acme?", "user_id": "demo"}'

Connect your agents (since v0.10.0)

One command configures the agents it detects:

pip install remembra
remembra-install --all --url http://localhost:8787

This auto-detects and configures: Claude Desktop, Claude Code, Codex CLI, Cursor, Gemini CLI. (Windsurf is unverified: remembra-install --agent windsurf writes it, --all does not.)

Verify setup:

remembra-doctor all

{
  "mcpServers": {
    "remembra": {
      "command": "remembra-mcp",
      "env": {
        "REMEMBRA_URL": "http://localhost:8787",
        "REMEMBRA_USER_ID": "default"
      }
    }
  }
}

Claude Code:

claude mcp add remembra -e REMEMBRA_URL=http://localhost:8787 -- remembra-mcp

Cursor — add to .cursor/mcp.json:

{
  "mcpServers": {
    "remembra": {
      "command": "remembra-mcp",
      "env": {
        "REMEMBRA_URL": "http://localhost:8787"
      }
    }
  }
}

Now ask Claude: "Remember that Alice is CEO of Acme Corp" — then later: "Who runs Acme?"

Python SDK

pip install remembra

from remembra import Memory

memory = Memory(user_id="user_123")
memory.store("Had a meeting with Sarah from Acme Corp. She prefers email over Slack.")
result = memory.recall("How should I contact Sarah?")
print(result.context)  # "Sarah from Acme Corp prefers email over Slack."

TypeScript SDK

npm install remembra

import { Remembra } from 'remembra';

const memory = new Remembra({ url: 'http://localhost:8787' });
await memory.store('User prefers dark mode');
const result = await memory.recall('preferences');

Memory features

🧠 Smart Extraction — LLM-powered fact extraction from raw text

👥 Entity Resolution — "Adam", "Mr. Smith", "my husband" → same person

⏱️ Temporal Memory — TTL, decay curves, historical queries

🔍 Hybrid Search — Semantic + keyword for accurate recall

🔒 Security — PII detection, anomaly monitoring, audit logs

📊 Dashboard — Visual memory browser, entity graphs, analytics

📊 Benchmarks

One small LoCoMo run, not a benchmark result: in March 2026 we ran 1 of the 10 LoCoMo conversations, 199 questions, judged by gpt-4o-mini. 76% overall. The 47 adversarial questions, whose answer is not in the conversation, all scored 0, because Remembra did not detect them; the other 152 questions scored 100%. The numbers are in benchmarks/results_20260307_040346_summary.json. A run over all 10 conversations has not been done yet.

Run it yourself: python benchmarks/locomo_runner.py --data /tmp/locomo/data/locomo10.json

📖 Documentation

🛠️ MCP Server

Give an MCP-capable coding agent persistent memory. Works with Claude Code, Cursor, VS Code + Copilot, Windsurf, JetBrains, Zed, OpenAI Codex, and any MCP-compatible client.

pip install remembra[mcp]
claude mcp add remembra -e REMEMBRA_URL=http://localhost:8787 -- remembra-mcp

Available tools (24):

🏗️ Architecture

┌─────────────────────────────────────────────────────────────┐
│                    Your Application                          │
├──────────┬──────────────┬───────────────────────────────────┤
│ Python   │ TypeScript   │ MCP Server (Claude/Cursor)        │
│ SDK      │ SDK          │ remembra-mcp                      │
├──────────┴──────────────┴───────────────────────────────────┤
│                   Remembra REST API                          │
├──────────────┬──────────────┬───────────────┬───────────────┤
│  Extraction  │   Entities   │   Retrieval   │   Security    │
│  (LLM)       │  (Graph)     │ (Hybrid)      │  (PII/Audit)  │
├──────────────┴──────────────┴───────────────┴───────────────┤
│                    Storage Layer                             │
│         Qdrant (vectors) + SQLite (metadata/graph)          │
└─────────────────────────────────────────────────────────────┘

🤝 Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

# Clone
git clone https://github.com/remembra-ai/remembra
cd remembra

# Install dev dependencies
pip install -e ".[dev]"

# Run tests
pytest

# Start dev server
remembra-server --reload

📄 License

MIT License — Use it however you want.

⭐ Star History

If Remembra helps you, please star the repo! It helps others discover the project.

Built with ❤️ by DolphyTech
remembra.dev • docs • twitter • discord