Fraise MCP server
Commit Nov 15, 2026Provides a temporal memory graph database that allows AI agents to remember and recall information using a specialized query language.
Also known as FraiseHQ/fraise
- Stars
- 8
- Tools
- 2
- Downloads, 30 days
- —
- Latest version
- 0.3.7
- Last commit
- Nov 15, 2026
- License
- MIT
What is Fraise MCP?
Fraise provides a temporal memory graph database that allows AI agents to remember and recall information using a specialized query language. It exposes 2 tools, such as recall, remember.
Summary generated from the project's README
About Fraise MCP server
Fraise provides a temporal memory graph database designed specifically for AI agents to store and retrieve information. It operates as a single binary that requires no external database infrastructure to provision. Developers can run it locally via Homebrew, Docker, or Go, and connect to it through a running daemon listening on port 9876. The system uses a specialized query language called FQL, which focuses on two primary verbs: remember and recall.
This memory system organizes knowledge into facts, entities, and topics, allowing for hybrid retrieval that combines full-text, graph, and vector search. Because it is temporal by default, the database automatically ranks recent memories higher than older ones. It is built to be extremely fast, with measured p50 search speeds significantly outperforming other agent memory systems. The server can host multiple independent memory graphs, which allows developers to isolate data by user, session, or specific agent using a simple addressing syntax.
What you can do with it
- 1Store new agent knowledgeAn AI agent can save a specific fact and categorize it by topic or entity using the remember command.
- 2Retrieve historical contextA developer can instruct an agent to look up past information related to a specific entity within a certain timeframe.
- 3Connect agents to memoryYou can use the MCP bridge to allow any MCP client to access the running Fraise daemon.
Written from the project's README. Every use case is checked against a quote from it.
How to install Fraise MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Fraise MCP in Claude Code
$ claude mcp add fraise -- docker run -i --rm ghcr.io/fraisehq/fraise:0.3.7 mcpInstall Fraise MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"fraise": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/fraisehq/fraise:0.3.7",
"mcp"
]
}
}
}Install Fraise MCP in VS Code
.vscode/mcp.json
{
"servers": {
"fraise": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/fraisehq/fraise:0.3.7",
"mcp"
]
}
}
}Install Fraise MCP in VS Code CLI
$ code --add-mcp '{"name":"fraise","type":"stdio","command":"docker","args":["run","-i","--rm","ghcr.io/fraisehq/fraise:0.3.7","mcp"]}'Install Fraise MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"fraise": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/fraisehq/fraise:0.3.7",
"mcp"
]
}
}
}Install Fraise MCP in Codex
$ codex mcp add fraise -- docker run -i --rm ghcr.io/fraisehq/fraise:0.3.7 mcpInstall Fraise MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.fraise] command = "docker" args = ["run", "-i", "--rm", "ghcr.io/fraisehq/fraise:0.3.7", "mcp"]
Install Fraise MCP in Gemini CLI
$ gemini mcp add -s user fraise docker -- run -i --rm ghcr.io/fraisehq/fraise:0.3.7 mcpInstall Fraise MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"fraise": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/fraisehq/fraise:0.3.7",
"mcp"
]
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for ghcr.io/fraisehq/fraise:0.3.7 0.3.7 in an isolated container with no network and no keys. It answered and listed 2 tools.
Fraise MCP tools 2
Read from the server with tools/listrecallSearch the agent's long-term memory: run an FQL recall against the fraise daemon and return the matching facts ranked by relevance and recency. Anchors alone — topic:/entity: with no search terms and no vector — seed the search with every fact filed under them, scored one unit per named anchor and decayed by age, newest first under a single anchor: the way to see what is stored under a topic before you know what to search for.
rememberStore a self-contained fact in the agent's long-term memory: run an FQL remember against the fraise daemon.
Automated checks
Ran Nov 13, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablefraisehq/fraise is public and reachablegithub.com/fraisehq/fraise ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-12github.com/fraisehq/fraise ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubFraise
Fraise is a memory database for AI agents. One they query directly, in a language built for tokens, not humans.
remember 'acme moved to annual billing' topic:billing entity:acme
recall billing entity:acme since:30d top:5
Two verbs. One binary. No infrastructure to run.
Install
brew install fraisehq/tap/fraise
brew services start fraise
curl -X POST localhost:9876/api/v1/q -H 'content-type: application/json' \
-d "{\"query\": \"remember 'the parrot is turquoise' topic:color\"}"
Linux packages, Docker, go install and signed release binaries are all in Get Started below.
Read Durability before you deploy. Persistence is issue #171 and the next major piece of work.
How it compares
Measured on LoCoMo — 10 multi-session conversations, 1,986 questions — with every system ingesting the same conversations, using the same extraction model and the same embedding model, and answering the same questions. k=10, full data, latest run per system as of 2026-10-11.
| system | retrieval recall | p50 search | memory tokens |
|---|---|---|---|
| fraise 0.3.3 | 0.910 | 0.185 s | 7,453,109 |
| hindsight 0.9.2 | 0.913 | 5.836 s | 1,688,873 |
| everos 1.2.3 | 0.897 | 0.376 s | 10,030,966 |
| letta 0.16.8 | 0.897 | 0.349 s | 226,854 |
| mem0 2.0.18 | 0.886 | 0.576 s | 4,120,078 |
| memos 2.0.33 | 0.865 | 0.307 s | 4,000,552 |
| graphiti 0.30.2 | 0.828 | 0.290 s | 9,861,973 |
| cognee 1.5.3 | 0.790 | 6.273 s | 8,526,019 |
| langmem 0.0.30 | 0.783 | 0.227 s | 1,078,110 |
Fraise comes within 0.003 of the best recall, 31× faster than the one system that reaches it. Near enough the same evidence, in a fraction of the time. The token column is the price of that recall: the extractor (fraise-sdk 0.2.0) reads each message beside what the graph already holds, and that context is where the recall came from.
These come from agent-memory-benchmarks, an open harness — precision, recall and F1 across k ∈ {1, 3, 5, 10}, per category, every run tagged and reproducible from the tag. The full tables are in its RESULTS.md.
Why Fraise
- A query language agents can actually write. FQL has two verbs —
rememberandrecall— and one way to say each thing. Fewer degrees of freedom means fewer ways for a model to get it wrong, and fewer tokens spent saying it. - Hybrid retrieval. Facts are indexed for full-text, graph, and (optionally) vector search. One query, ranked across all three.
- Temporal by default. Recent memories outrank older ones, so recall is recency-aware without asking for it.
- The fastest system measured. 0.185 s p50 on LoCoMo, ahead of every other system and 31× faster than the one with matching recall. Remember and recall mid-step, while the user waits.
- No infrastructure. A single binary. No database to provision, no service to stand up beside it.
- Open source, MIT.
Status
v0.3.3. The core loop works end to end and the install paths are verified on clean machines. The benchmark row above was produced from this release. 0.4.0 (late October) changes the scorer and adds explain and describe; 0.5.0 (November) is persistence and forget.
Good for building agent memory today. Not yet for long term production use.
How it works
Fraise stores knowledge as a temporal memory graph built from three kinds of node:
- facts — the things you remember, one statement each
- entities — who or what a fact mentions
- topics — what a fact is about
Edges connect facts to the entities they mention and the topics they're about, so a query can start from either side. A recall finds seed facts by text and, optionally, by vector similarity; a recall that names only topics or entities starts from the facts filed under them. With depth:1 or depth:2, a named topic or entity whose facts matched better than its size predicts passes that evidence on to the rest of its facts. Results are ranked by relevance and recency, and the best top come back.
Ranking is not a black box: a fact's score folds its own match strength with what it receives through anchors carrying more mass than their size would predict, each measured against the facts the recall could return. The background rate that "more" is measured against is estimated per query, from the part of the graph the query touched, so there is no relevance constant to tune. Hybrid retrieval has the full model.
A single Fraise instance holds several independent memory graphs (8 by default), addressed with @N — one per user, per session, per agent, however you like.
Get Started
Fraise is a single binary — no database to provision, nothing to configure. Every route below leaves you with a server listening on port 9876, at localhost:9876.
With Homebrew
brew install fraisehq/tap/fraise
brew services start fraise
The service survives crashes and restarts on login (keep_alive), logs to $(brew --prefix)/var/log/fraise.log, and reads its config from $(brew --prefix)/etc/fraise/fraise.config.toml — installed with every setting commented at its default, and never overwritten on upgrade.
With Docker
docker run -p 127.0.0.1:9876:9876 ghcr.io/fraisehq/fraise:latest
Published tags: one per release, latest for the newest stable, edge for the tip of main, and an immutable full-commit-SHA tag for every merge that touches the server.
Images are built with SLSA provenance, verifiable without pulling:
gh attestation verify oci://ghcr.io/fraisehq/fraise:latest --repo FraiseHQ/fraise
With Go
go install github.com/FraiseHQ/fraise/cmd/server@latest
"$(go env GOPATH)/bin/server"
The binary installs as server, after its package path — rename it to fraise if that reads better.
Nothing further is needed to trust this: the Go toolchain checks every module download against the public checksum transparency log, and your own machine compiles the result.
Linux packages
.deb and .rpm packages ship with every release, with a systemd user unit:
VERSION=0.3.0
ARCH=$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/')
curl -sSfLO "https://github.com/FraiseHQ/fraise/releases/download/v${VERSION}/fraise_${VERSION}_linux_${ARCH}.deb"
sudo dpkg -i "fraise_${VERSION}_linux_${ARCH}.deb"
systemctl --user enable --now fraise
Logs go to the journal (journalctl --user -u fraise -f), and the unit reads ~/.config/fraise/fraise.config.toml when present — a shipped default with every setting commented lives at /etc/fraise/fraise.config.toml to copy from. For agents that outlive your login session, let the user manager keep running: loginctl enable-linger $USER. A system-level (shared server) variant of the unit is described in Running as a managed service.
From a release binary
VERSION=0.3.0
OS=$(uname -s | tr '[:upper:]' '[:lower:]') # linux | darwin
ARCH=$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/') # amd64 | arm64
ASSET="fraise_${VERSION}_${OS}_${ARCH}.tar.gz"
BASE="https://github.com/FraiseHQ/fraise/releases/download/v${VERSION}"
curl -sSfLO "${BASE}/${ASSET}"
tar xzf "$ASSET"
./fraise
Windows builds ship as .zip under the same naming scheme.
Verify a release
Releases carry a cosign signature over checksums.txt, using the same VERSION and BASE as above:
curl -sSfLO "${BASE}/checksums.txt"
curl -sSfLO "${BASE}/checksums.txt.sigstore.json"
# 1. the bundle proves checksums.txt came from this repo's release workflow
cosign verify-blob \
--bundle checksums.txt.sigstore.json \
--certificate-identity-regexp 'https://github.com/FraiseHQ/fraise/.github/workflows/go.yaml@refs/tags/v.*' \
--certificate-oidc-issuer https://token.actions.githubusercontent.com \
checksums.txt
# 2. checksums.txt proves your archive is the one it covers
sha256sum --ignore-missing -c checksums.txt # macOS: shasum -a 256 --ignore-missing -c
Run from source
git clone https://github.com/FraiseHQ/fraise
cd fraise
make dev
Your first memory
curl -X POST localhost:9876/api/v1/q \
-H 'content-type: application/json' \
-d "{\"query\": \"remember 'the parrot is turquoise' topic:color\"}"
curl -X POST localhost:9876/api/v1/q \
-H 'content-type: application/json' \
-d '{"query":"recall parrot"}'
{
"results": {
"count": 1,
"hits": [
{ "value": "the parrot is turquoise", "timestamp": "...", "score": 0.2867 }
]
}
}
Use it from an agent
MCP
fraise mcp is a stdio MCP server — a thin bridge to a running daemon, so any MCP client can remember and recall. It exposes two tools, recall and remember, and needs no flags when the daemon is on its default address.
Start the daemon first (brew services start fraise, or systemctl --user start fraise on Linux), then register the bridge with whichever coding agent you use.
Claude Code
claude mcp add fraise -- fraise mcp
That registers it for the current project; add --scope user to make it available in every project instead.
Codex
codex mcp add fraise -- fraise mcp
Or write it into ~/.codex/config.toml directly:
[mcp_servers.fraise]
command = "fraise"
args = ["mcp"]
OpenCode
Add it to opencode.json in your project root:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"fraise": {
"type": "local",
"command": ["fraise", "mcp"]
}
}
}
Any other client
{
"mcpServers": {
"fraise": { "command": "fraise", "args": ["mcp"] }
}
}
The bridge describes itself over MCP: each tool arrives with a description and a full JSON schema for its arguments and results — the FQL shapes, a worked example, what a score means — so a client knows what recall and remember do and how to call them without being told. What a tool description cannot carry is the policy: the habit of reaching for memory unprompted, and the judgement about what is worth keeping. That belongs in the file your agent already reads — CLAUDE.md for Claude Code, AGENTS.md for Codex and OpenCode — and two habits are enough: recall before answering anything that leans on earlier decisions or preferences, and remember only facts that will still matter in a later session, one self-contained fact per call with the topics and entities that will make it findable.
SDKs
Python (sdk/python) — the only SDK today:
pip install --pre fraise-sdk
from fraise_sdk import FraiseClient
with FraiseClient("http://localhost:9876") as fraise:
fraise.remember("the parrot is turquoise", topics=["color"])
for hit in fraise.recall("parrot", top=5):
print(hit.value, hit.score)
The Python SDK is dependency-light and supports vector search when you supply an embedder. See its README for embeddings and the full API.
TypeScript — not available yet (#179). Until it lands, TypeScript callers use fraise mcp or talk to the HTTP endpoint directly; it is two verbs over one route, so a client is a short wrapper around fetch. See the HTTP API.
Claude Agent SDK
The Python SDK ships memory tools for the Claude Agent SDK, exposed as an in-process MCP server so the agent decides what to store and recall:
from claude_agent_sdk import ClaudeAgentOptions
from fraise_sdk import FraiseClient
from fraise_sdk.integrations.claude_agents import memory_server, allowed_tools
fraise = FraiseClient("http://localhost:9876")
options = ClaudeAgentOptions(
system_prompt="Remember durable facts the user shares, and recall them when relevant.",
mcp_servers={"fraise_memory": memory_server(fraise)},
allowed_tools=allowed_tools(),
)
A complete, Docker-runnable agent lives in examples/claude-agent-sdk.
OpenAI Agents SDK
memory_tools(client) returns bound recall and remember tools:
from agents import Agent, Runner
from fraise_sdk import FraiseClient
from fraise_sdk.integrations.openai_agents import memory_tools
fraise = FraiseClient("http://localhost:9876")
agent = Agent(
name="Assistant",
instructions="Remember durable facts the user shares, and recall them when relevant.",
tools=memory_tools(fraise),
)
result = Runner.run_sync(agent, "My favourite colour is orange.")
print(result.final_output)
A complete, Docker-runnable agent lives in examples/openai-agents.
References
Contributing
Contributions are welcome — see CONTRIBUTING.md for how to build, test, and submit changes.
Code of Conduct
This project follows the Contributor Covenant.
Community
Questions, ideas, or building something with Fraise? Join the Discord. Bugs and feature requests belong in issues so they don't get lost.
License
MIT — see LICENSE.
Fraise MCP questions
How do I add Fraise MCP to Claude Code?
Run claude mcp add fraise -- docker run -i --rm ghcr.io/fraisehq/fraise:0.3.7 mcp in your terminal. Add --scope user to make it available in every project.
How do I add Fraise 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 Fraise MCP provide?
It exposes 2 tools, including recall, remember.
What is Fraise used for?
Fraise is a memory database designed specifically for AI agents to store and retrieve information using a language optimized for tokens.
How does the retrieval system work?
It uses hybrid retrieval, indexing facts for full-text, graph, and optional vector search, then ranking them by relevance and recency.
Is Fraise suitable for long-term production use?
As of version 0.3.3, it is considered good for building agent memory today, but not yet recommended for long-term production use.