Fournit un wiki basé sur le markdown pour permettre aux agents de codage de stocker des décisions, de suivre la dérive de projet et de gérer des points de contrôle de session via MCP.
Aussi connu sous arnaugonzalez/memory-boost
- Étoiles
- 0
- Outils
- —
- Téléchargements, 30 jours
- 380
- Dernière version
- 0.2.1
- Dernier commit
- 14 nov. 2026
- Licence
- MIT
Qu'est-ce que memory-boost MCP ?
Fournit un wiki basé sur le markdown pour permettre aux agents de codage de stocker des décisions, de suivre la dérive de projet et de gérer des points de contrôle de session via MCP.
Résumé généré à partir du README du projet
À propos du MCP server memory-boost
memory-boost fournit un système de wiki basé sur le markdown conçu pour aider les agents de codage à maintenir une mémoire à long terme et à suivre l'évolution d'un projet. Il fonctionne comme un dépôt local de décisions, de projets et de concepts stockés dans des fichiers markdown simples au sein du répertoire de partage local de l'utilisateur. Les développeurs peuvent connecter divers clients IA comme Claude Code, Cursor, Codex ou Gemini CLI via MCP en utilisant les transports stdio ou HTTP.
Le serveur inclut neuf outils spécialisés tels que memory_drift, memory_lesson et memory_checkpoint pour gérer l'information. Il se distingue par sa capacité à auditer la propre mémoire de l'agent pour identifier les décisions obsolètes ou expirées grâce à la commande drift. Il dispose également d'une commande mine qui analyse les transcriptions locales pour rendre compte de l'utilisation des outils, des commandes échouées et de la discipline des sessions. Cela permet aux développeurs de vérifier si un agent lit de manière répétée les mêmes fichiers ou s'il génère un nombre excessif de sous-agents.
Ce que vous pouvez faire avec
- 1Récupérer le contexte après une compactionUtilisez les points de contrôle de session pour restaurer les informations après que la fenêtre de contexte d'un agent a été compressée.
Extrait du README du projet. Chaque cas d'utilisation est vérifié par rapport à une citation du document.
Comment installer memory-boost MCP
Formats vérifiés le 10 nov. 2026Ajouter à CursorAjouter à GooseInstaller memory-boost MCP dans Claude Code
$ claude mcp add memory-boost -- uvx memory-boostInstaller memory-boost MCP dans Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"memory-boost": {
"command": "uvx",
"args": [
"memory-boost"
]
}
}
}Installer memory-boost MCP dans VS Code
.vscode/mcp.json
{
"servers": {
"memory-boost": {
"type": "stdio",
"command": "uvx",
"args": [
"memory-boost"
]
}
}
}Installer memory-boost MCP dans VS Code CLI
$ code --add-mcp '{"name":"memory-boost","type":"stdio","command":"uvx","args":["memory-boost"]}'Installer memory-boost MCP dans Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"memory-boost": {
"command": "uvx",
"args": [
"memory-boost"
]
}
}
}Installer memory-boost MCP dans Codex
$ codex mcp add memory-boost -- uvx memory-boostInstaller memory-boost MCP dans Codex config.toml
~/.codex/config.toml
[mcp_servers.memory-boost] command = "uvx" args = ["memory-boost"]
Installer memory-boost MCP dans Gemini CLI
$ gemini mcp add -s user memory-boost uvx -- memory-boostInstaller memory-boost MCP dans Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"memory-boost": {
"command": "uvx",
"args": [
"memory-boost"
]
}
}
}Configuration
MEMORY_BOOST_SEMANTIC
| Nom | Description | Type |
|---|---|---|
| MEMORY_BOOST_SEMANTIC | — |
Vérifications automatisées
Exécuté le 14 nov. 2026Rapport complet →A passé nos vérifications automatisées. Il ne s'agit pas d'un audit de sécurité : lisez le code et donnez au serveur l'accès le plus restreint dont il a besoin. Fonctionnement des vérifications
- Dépôt source lié et accessiblearnaugonzalez/memory-boost is public and reachablegithub.com/arnaugonzalez/memory-boost ↗Réussi
- Le nom du package correspond au dépôt sourcememory-boost names arnaugonzalez/memory-boost as sourcepypi.org/project/memory-boost/ ↗Réussi
- Provenance du build (attestation Sigstore)Sigstore attestation for memory-boostpypi.org/project/memory-boost/ ↗Réussi
- Licence open source (OSI)MITspdx.org/licenses/MIT.html ↗Réussi
- Commit ou version publiée au cours de l'année écouléeLast commit or release 2026-11-09github.com/arnaugonzalez/memory-boost ↗Réussi
- OpenSSF ScorecardNon vérifié
- Nom du package non proche d'un package populaireNo popular package one edit away from memory-boostRéussi
- Aucun avis critique dans le package ou ses dépendances30 resolved dependencies checked; no critical advisoryosv.dev ↗Réussi
- Aucune instruction cachée destinée au modèle0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersRéussi
- Les outils destructifs sont étiquetésNon vérifié
- Le point de terminaison distant répond à la poignée de main MCPNon vérifié
README
Voir sur GitHubYour agents write everything down. Nobody reads it back.
Every memory tool for coding agents helps them remember more. None of them mention that half of what they remember expired in July. memory-boost keeps a plain-markdown memory your agents read and write over MCP, and then does the unglamorous part: it audits that memory and your own sessions, and tells you what drifted. Politely, with numbers.
Think of it as a code review for what your agents remember and a fitness tracker for how you work
with them. Mostly the fitness tracker: mine told me my most-failed command was cd. Sixty-nine
times.
What it answers
| You wonder… | memory-boost answers |
|---|---|
| Which decisions quietly expired while we were busy shipping? | drift: review_by 2026-07-08, 78 days ago |
| Which "active" projects actually died months ago? | drift: last session 161 days ago; still listed as live |
| We fixed this exact bug in another repo. How? | lessons: the fix follows you to every project with the same stack |
| Why does my agent keep re-reading the same file? | mine: one file, read 18 times |
| Is my agent spawning 20 subagents behind my back? | mine: yes, and in which session |
Where was I before /compact ate my context? |
The session-start hook puts your checkpoint back |
Using an AI agent? Point Claude Code, Codex, Cursor or Gemini CLI at this repo: AGENTS.md tells it how to install memory-boost, seed a wiki and run the reports for you.
Try it in 30 seconds
No install needed; the wiki lands in ~/.local/share/memory-boost:
uvx memory-boost==0.2.1 init --example # sample wiki with five kinds of rot + four synthetic transcripts
uvx memory-boost==0.2.1 drift # what in that memory is stale, orphaned or never written down
uvx memory-boost==0.2.1 mine # now on your real ~/.claude/projects: aggregates only
To keep it in Claude Code, install the plugin. It brings the MCP server, the session-start brief and the skills in one step; it only needs uv on your PATH.
/plugin marketplace add arnaugonzalez/memory-boost
/plugin install memory-boost@memory-boost
Other agents, or the CLI on its own: uv tool install memory-boost==0.2.1 (or
pipx install memory-boost==0.2.1). Or let your agent do it: see Install from your agent.
Install from your agent
Paste this into Claude Code, Codex, Cline or Cursor:
Install memory-boost 0.2.1 by following https://github.com/arnaugonzalez/memory-boost/blob/main/llms-install.md : install the CLI with
uv tool install memory-boost==0.2.1, runmemory-boost init, registermemory-boost serveas a stdio MCP server namedmemory, check that it answers with ninememory_*tools, then runmemory-boost driftand show me the output. Ask me before writing outside the memory home (~/.local/share/memory-boost) or editing any global agent config.
The agent-oriented steps (stdio and serve --http, per harness, with checks) are in
llms-install.md.
Example: back on a project after two months
You come back to acme-api and the agent still trusts everything it wrote down. drift says
which of it no longer holds: a Postgres pin whose review date passed in June, a superseded decision
that points nowhere, projects that went silent. page shows why the pin was made, so you can
decide in a minute. lessons brings over what pixel-notes learned about retrying jobs, because
both projects run background jobs. Bundled example data (memory-boost init --example), recorded
with vhs from docs/demo.tape.
On a real machine
Five weeks of the author's own daily use: 29 decisions, 24 projects, 657 Claude Code transcripts. Output as produced; only project and file names are replaced.
$ memory-boost drift
# Drift report — 2026-09-24
29 decisions · 24 projects · 204 log entries · 33 open checkpoints · **20 findings**
## decision-expired (9)
- deploy-via-bastion — review_by 2026-07-08 (78 days ago); revisit or mark historic
- bot-guardrails — review_by 2026-07-08 (78 days ago); revisit or mark historic
…
## project-no-decisions (2)
- thesis-solver — 20 sessions logged, 0 decisions tagged 'thesis-solver': the learning lives only in transcripts
## project-silent (5)
- mood-api — last session 2026-04-16 (161 days ago); still listed as live
…
$ memory-boost mine
# Session digest — 2026-09-24
sessions 80 with ≥20 turns
tools Bash 5956 · Edit 860 · Read 692 · Write 493 · Agent 203 · ToolSearch 138
bash 5956 calls, 159 failed (2.7%); most failed: cd (69), sleep (12), ssh (9), pkill (8), ls (7)
bash/edit 4.4x; extreme: worktree-a 107.5x, sandbox 70.0x, sandbox 54.0x
reads 692 calls, 131 re-reads of a file already read (19%); top: …/apply_email.py ×18
discipline 62 long sessions (≥60 turns): 47 never checkpointed, 29 never saved
subagents 203 spawned in 44 sessions; max in one session: 20
Every line is a habit to change, a decision to revisit, or a rule worth writing down. None of it needed a new tool: the data was already on disk. It needed a reader.
What it is
- A wiki you own.
projects/*.md,decisions/*.md,concepts/*.md,log.md. Plain markdown; edit by hand, keep it in git. SQLite FTS5 index as a disposable cache. Nine MCP tools for any harness:memory_brief,memory_recall,memory_page,memory_save,memory_checkpoint,memory_resume,memory_drift,memory_lesson,memory_shelf.memory_shelf(CLI:memory-boost shelf "idea") appends a dated one-line idea toconcepts/idea-shelf.mdwithout the agent reading the page back. - Freshness as data. Decisions carry
status:andreview_by:. Search results are taggedcurrent / unclassified / review / historic / superseded, current first. - Session checkpoints that survive
/compact, with one line per other active session on the same project so parallel agents don't collide. driftreads the wiki and reports what expired, what went silent, what was never written down and what was left half-done. The current project's top findings go into every session brief.minereads your local Claude Code transcripts and reports tool usage, failed commands, re-reads, subagent fan-out and checkpoint discipline. Aggregates only: no prompt, command or file content is stored or printed, so the digest is safe to paste anywhere.lessons:concepts/pages withapplies_when: [tags]. A project page that lists matchingtags:gets those lessons in its brief, so what worked in one repo reaches the next. The/retroskill writes them at session end.
Connect your harness
MCP server (all harnesses): command memory-boost, args ["serve"].
To share one server between several sessions, run it over streamable HTTP (stateless, JSON
responses) and point each harness at http://127.0.0.1:8765/mcp:
memory-boost serve --http # --host 127.0.0.1 --port 8765 are the defaults
claude mcp add --transport http memory -s user http://127.0.0.1:8765/mcp
It binds to loopback by default and has no authentication: keep it there.
| Harness | MCP registration | Context at session start |
|---|---|---|
| Claude Code (plugin) | /plugin install memory-boost@memory-boost |
Included: hook, MCP server, skills |
| Claude Code (manual) | claude mcp add memory -s user -- memory-boost serve |
Hook below (startup, resume, compact); mine reads its transcripts |
| Codex CLI | codex mcp add memory -- memory-boost serve |
AGENTS.md: "call memory_brief first" |
| Cursor / VS Code / Gemini CLI | stdio entry in their mcp.json / settings.json |
Same line in rules (hook adapters: roadmap) |
Manual Claude Code hooks (~/.claude/settings.json), not needed with the plugin:
{ "hooks": {
"SessionStart": [ { "hooks": [ { "type": "command", "command": "memory-boost hook session-start" } ] } ],
"Stop": [ { "hooks": [ { "type": "command", "command": "memory-boost hook stop", "timeout": 10 } ] } ],
"PreCompact": [ { "hooks": [ { "type": "command", "command": "memory-boost hook pre-compact", "timeout": 20 } ] } ]
} }
On startup/resume it injects ~1k tokens: catalog, the project's context and last sessions,
its drift, open pending items, lessons from other projects, your open checkpoint. On compact
only this session's checkpoint. It never blocks session start: on any error it prints nothing.
stop and pre-compact write an automatic checkpoint from the transcript, with no LLM call:
your prompts (minus <private>…</private>), files edited and git commits, under the checkpoint's
auto key. What the agent wrote (task, done, next) is never overwritten. stop writes only when
something changed and 10 minutes or 4 prompts passed; pre-compact always writes, so the
post-compact re-injection has something to show even if the agent never called memory_checkpoint.
Skills: /memory-boost (router: when to run what), /save-session, /restore-session,
/retro. The plugin installs them as /memory-boost:retro and so on; without it, copy
skills/* into ~/.claude/skills/. The first session after installing the plugin takes a few
extra seconds while uv fetches memory-boost==0.2.1 and its dependencies from PyPI (the only
network access the plugin makes); later sessions start in about 0.2 s.
CLI contract for agents: data on stdout, errors on stderr with a fix: line, --json on every
reading command (with a version field), exit 0 = trust stdout, 1 = not found, 2 = bad input.
Reports end with a next: line naming the exact command to run.
How it works
Source: docs/architecture.mmd
The project is resolved from the working directory name (~/work/acme-api → projects/acme-api.md);
map other names in aliases.json. Under 1,900 lines of Python, one dependency (mcp), no
embeddings unless you opt into semantic recall, no daemon unless you run serve --http.
Session events v2
Every memory_save (or memory-boost save) writes one event to $MEMORY_BOOST_HOME/events/<agent>/<YYYY-MM-DD>.jsonl
and one entry to wiki/log.md. The v2 fields are all optional: a v1 call (project, action, result,
detail, pending as text) keeps working and writes the same log.md header. Each event now carries
"schema": "memory-boost/session@2", a server date_local, a per-session seq and the assigned pending ids;
v1 readers ignore the extra keys.
outcome:done | progress | blocked | waiting | research | abandoned.pending: a list of{text, owner, severity, due?, waiting_on?}. The server assigns each item a stable id<project>#<n>(counter per project inevents/pending-seq.json), shown in the brief underopen pending.closes/drops: ids the session finished or no longer needs. Open items are what remains after folding them.sessionandmetrics: optional blocks stored as given. The caller computes them, for example with a session summary tool; the save itself does not read transcripts.
{
"schema": "memory-boost/session@2",
"project": "acme-api",
"action": "Moved the job queue to Postgres and added retries",
"result": "ok",
"outcome": "progress",
"session": {"id": "3f9c2a1e-…", "harness": "claude-code", "cwd": "/home/me/work/acme-api",
"segment_start": "2026-10-28T10:00:03Z", "segment_end": "2026-10-28T14:45:12Z"},
"metrics": {"source": "ledger session-summary@1", "minutes": {"acme-api": {"attention": 182, "agent": 160, "gross": 230}},
"commits": [{"repo": "acme-api", "sha": "f2c1114", "pushed": false}],
"tests": {"runs": 6, "passed": 1180, "failed": 0}, "cost_usd": 14.2},
"pending": [{"text": "Run the batch import", "owner": "user", "severity": 3},
{"text": "Push main to origin", "owner": "user", "severity": 2}],
"closes": ["acme-api#12", "acme-api#14"]
}
date_local is set by the server from MEMORY_BOOST_TZ (an IANA zone such as Europe/Madrid; UTC by default).
Events written before v2 have no pending ids, so memory-boost pending [--project] (and closes) cannot see them.
Semantic recall (optional)
Off by default: memory_recall is full-text only and the base install stays one dependency.
To also match paraphrases and other languages, run a local embedding model:
pip install "memory-boost[semantic]==0.2.1" # adds sqlite-vec
ollama pull embeddinggemma
export MEMORY_BOOST_SEMANTIC=1
memory-boost index # embeds the wiki once; later runs embed only changes
The first index of a large wiki on CPU can take minutes: as a rough guide, about 15 minutes for some
850 documents on a laptop without a GPU (one measurement, not a benchmark). memory-boost index and
recall show embedding N/M chunks… on stderr while it runs; later runs re-embed only what changed.
Default mode when on is hybrid (full-text and vectors fused by weighted reciprocal rank); override
with MEMORY_BOOST_RECALL_MODE=fts|semantic|hybrid or memory-boost recall --mode. If Ollama is down,
recall falls back to full-text and logs a warning. On a private 64-query set (39 literal, 25 paraphrase)
with a warm index on CPU: paraphrase nDCG@10 0.46 to 0.76, literal 0.80 to 0.85, p50 about 110 ms per query.
The query set is not published.
Configuration
| Variable | Default | Purpose |
|---|---|---|
MEMORY_BOOST_HOME |
$XDG_DATA_HOME/memory-boost |
Wiki, events, checkpoints, aliases.json |
MEMORY_BOOST_WIKI |
$MEMORY_BOOST_HOME/wiki |
Point at an existing wiki (e.g. a git repo) |
MEMORY_BOOST_INDEX |
$XDG_CACHE_HOME/memory-boost/index-<hash>.db |
Search index |
MEMORY_BOOST_CHECKPOINTS |
$MEMORY_BOOST_HOME/checkpoints |
Checkpoint directory |
MEMORY_BOOST_TRANSCRIPTS |
~/.claude/projects |
Where mine looks (several dirs: a:b) |
MEMORY_BOOST_TODAY |
today (UTC) | Pin the date for reproducible reports |
MEMORY_BOOST_TZ |
UTC |
IANA zone for date_local in events (e.g. Europe/Madrid) |
MEMORY_BOOST_AUTOSAVE_SECS |
600 |
hook stop: minimum seconds between automatic checkpoints |
MEMORY_BOOST_AUTOSAVE_TURNS |
4 |
hook stop: or this many new prompts, whichever comes first |
MEMORY_BOOST_SEMANTIC |
unset | 1 enables vector recall (needs memory-boost[semantic] + Ollama) |
MEMORY_BOOST_RECALL_MODE |
fts (hybrid with semantic) |
fts, semantic or hybrid |
MEMORY_BOOST_EMBED_MODEL |
embeddinggemma |
Ollama embedding model |
MEMORY_BOOST_OLLAMA_URL |
http://localhost:11434 |
Ollama endpoint |
Status values: current, review, historic, superseded; accepted/active read as
current and proposed as review.
Experimental (shipped, little real use yet): memory_shelf, memory-boost friction and the
lesson fields cue/evidence/confidence. Their output format may still change.
vs. alternatives
| memory-boost | basic-memory | claude-mem | agent-retro | |
|---|---|---|---|---|
| Store | Markdown wiki you edit | Markdown | Captured observations | None (prompt skill) |
| Search | FTS5 (+ optional local vectors) | FTS + vectors | FTS + vectors | — |
| Freshness / review dates | Yes | No | No | — |
| Drift report over memory | Yes | No | No | No |
| Session analytics | Yes (aggregates, local) | No | No | LLM reads the conversation |
| Parallel-session awareness | Yes | No | No | — |
| License | MIT | AGPL-3.0 | Apache-2.0 | ? |
Want better search, more integrations and a community? Use basic-memory. Want everything captured automatically? claude-mem. Use memory-boost if you want to learn from what your agents already wrote down.
Limits / non-goals
- Full-text search by default; embeddings only with the optional
[semantic]extra and a local Ollama. mineunderstands Claude Code transcripts today. Codex is on the roadmap.- Reports are as good as the wiki: an empty wiki yields an empty
drift. - Single user, local files. Linux and macOS; Windows untested.
- The wiki is read by your agents as instructions. Only use a wiki you trust; see SECURITY.md.
License
MIT
Questions sur memory-boost MCP
Comment ajouter memory-boost MCP à Claude Code ?
Exécutez claude mcp add memory-boost -- uvx memory-boost dans votre terminal. Ajoutez --scope user pour le rendre disponible dans tous les projets.
Comment ajouter memory-boost MCP à Cursor ?
Ouvrez ~/.cursor/mcp.json et ajoutez le serveur sous mcpServers, avec la configuration Cursor indiquée dans la section d'installation ci-dessus.
Que fait memory-boost pour les agents de codage ?
Il maintient une mémoire en markdown brut que les agents peuvent lire et écrire, tout en auditant cette mémoire pour détecter les informations obsolètes ou la dérive de projet.
Comment puis-je l'installer pour Claude Code ?
Vous pouvez l'installer en tant que plugin en utilisant la commande /plugin install memory-boost@memory-boost directement dans l'interface de Claude Code.
Est-ce que mes prompts privés sont stockés ?
Non, la commande 'mine' agrège des statistiques d'utilisation sans stocker ni afficher le contenu des prompts, des commandes ou des fichiers, ce qui rend le rapport sûr à partager.
Puis-je l'utiliser avec d'autres agents IA ?
Oui, il prend en charge d'autres agents comme Codex, Cursor ou Gemini CLI via les transports stdio ou HTTP.