Power your agent
Perintah milik penerbit sendiri. Bukan endpoint PlugMCP.
Host a copy with our keys and logs.
mcpb https://github.com/PeterPirog/mcp-light-memory/releases/download/v1.8.1/mcp-light-memory-1.8.1.mcpbClaude Code tidak punya tautan instal untuk perintah lokal. Salin perintah di bawah dan jalankan di terminal.
claude mcp add io.github.peterpirog-mcp-light-memory -- mcpb https://github.com/PeterPirog/mcp-light-memory/releases/download/v1.8.1/mcp-light-memory-1.8.1.mcpbJalankan di terminal.
{ "mcpServers": { "io.github.peterpirog-mcp-light-memory": { "command": "mcpb", "args": [ "https://github.com/PeterPirog/mcp-light-memory/releases/download/v1.8.1/mcp-light-memory-1.8.1.mcpb" ] } }}claude_desktop_config.json
URL remote atau perintah di mesin Anda? Perbedaan kedua cara instal
Jalankan di PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
BukaDari penerbit
MCP Light Memory is a lightweight, local-first, persistent memory system for coding agents and MCP clients (Warp, OpenCode, JetBrains AI Assistant / PyCharm, Claude Code, Cursor). It acts as a checkpoint + retrieval layer — it stores the minimum durable state needed to resume complex work across sessions, without keeping the full conversation in the model's context window.
Local-first persistent memory for coding agents and MCP clients.
When your agent starts a task, it calls context and gets back relevant past decisions, gotchas, constraints, and hypotheses — ranked, deduplicated, and trust-bounded. When it finishes, it checkpoints the working state. Next session, even after a restart, the memory is there.
.md file with YAML frontmatter (id, type, status, tags, sources, links, valid_from, valid_to, supersedes). Human-readable, diffable, durable.remember → update → supersede (links both directions, never deletes history) → forget (archives, never deletes) → timeline (temporal view). search --at YYYY-MM-DD for historical queries.=== BEGIN/END INTERNAL_RAG MEMORY === with a SECURITY NOTICE header. Structured JSON/MCP carries trust: untrusted + optional security_flags: ["instruction_like_content"].evidence_state (present/missing/unverifiable) for local path-like evidence — derived at retrieval time, never persisted.write:false blocks mutating tools before spawning a child. Per-call subprocess isolation (no shared state).py launcher, python, or python3 — the installer auto-detects the real interpreter and rejects the WindowsApps stub)pip install sentence-transformers numpy for better semantic retrievalThe current version is defined by the VERSION file — check it (or run mlm.py --version) instead of hard-coding an expected number.
Clone this repo once, then install into any project:
# Windows (PowerShell)
git clone https://github.com/PeterPirog/mcp-light-memory.git ~/mcp-light-memory
python ~/mcp-light-memory/install.py . --client warp
# Linux/macOS
git clone https://github.com/PeterPirog/mcp-light-memory.git ~/mcp-light-memory
python3 ~/mcp-light-memory/install.py . --client warp
The installer:
INTERNAL_RAG/ + AGENTS.mdinit + checkpoint + validate (so guard is OK immediately)MANUAL_REQUIRED / prints JetBrains instructions)python .agents\skills\internal-rag\mlm.py --version # reports the installed version
python .agents\skills\internal-rag\mlm.py status # expect: INTERNAL_RAG ready
python .agents\skills\internal-rag\mlm.py guard # expect: GUARD OK
One installer, four clients, two config scopes. Full guide: docs/INSTALLATION.md.
--global changes the scope of the CLIENT CONFIG (~/.warp/.mcp.json vs {repo}/.warp/.mcp.json, ~/.config/opencode/opencode.json vs project opencode.json). The server still points at the target project you installed into.You can paste one of these directly into the client agent. Replace C:\Projects\App with the real target repository path.
Warp — install for one project:
Install and configure MCP Light Memory (mcp-light-memory) as an MCP server for project C:\Projects\App in Warp, using project scope. Use the repository https://github.com/PeterPirog/mcp-light-memory. If the tool is not cloned yet, clone it to a stable location outside the project; if it already exists, update it with git pull --ff-only. Apply the canonical installation contract from the repository and run install.py with TARGET_PROJECT=C:\Projects\App and --client warp without --global. Do not force-overwrite an existing configuration. After installation, verify from cwd=C:\Projects\App: mlm.py --version, mlm.py status, and mlm.py guard, and confirm that the Warp configuration contains mcp-light-memory and the C:\Projects\App path. Report success only after MCP REGISTRATION: REGISTERED and successful verification. If Warp requires an additional project activation/toggle/approval, state the exact client-side step and do not claim the server is active before it is completed.
Warp — global client config for one project:
Install and configure MCP Light Memory (mcp-light-memory) in Warp globally for project C:\Projects\App. Use the repository https://github.com/PeterPirog/mcp-light-memory. If the tool is not cloned yet, clone it to a stable location outside the project; if it already exists, run git pull --ff-only. Apply the canonical installation contract and run install.py with TARGET_PROJECT=C:\Projects\App, --client warp, and --global. Remember: --global means the global Warp client configuration, while the server must still be bound to C:\Projects\App; do not use the multi-project router. After installation, verify from cwd=C:\Projects\App: mlm.py --version, mlm.py status, and mlm.py guard, and confirm that the global Warp configuration contains mcp-light-memory and the C:\Projects\App path. Report success only after MCP REGISTRATION: REGISTERED and successful verification.
OpenCode — install for one project (stable/V1):
Install and configure MCP Light Memory (mcp-light-memory) as an MCP server for project C:\Projects\App in OpenCode. By "OpenCode" I mean stable/V1, so use --client opencode, not opencode2. Use the repository https://github.com/PeterPirog/mcp-light-memory. If the tool is not cloned yet, clone it to a stable location outside the project; if it already exists, run git pull --ff-only. Run install.py with TARGET_PROJECT=C:\Projects\App and --client opencode without --global. Do not force-overwrite an existing configuration. If the installer returns MCP REGISTRATION: MANUAL_REQUIRED (for example because opencode.jsonc exists), do not report success: safely edit the JSONC while preserving comments and unrelated settings if you have appropriate file-editing tools; otherwise report the exact manual action required. After real registration, verify from cwd=C:\Projects\App: mlm.py --version, mlm.py status, and mlm.py guard, and confirm that the OpenCode configuration contains mcp-light-memory and C:\Projects\App.
OpenCode — global client config for one project (stable/V1):
Install and configure MCP Light Memory (mcp-light-memory) globally in OpenCode for project C:\Projects\App. By "OpenCode" I mean stable/V1, so use --client opencode. Use the repository https://github.com/PeterPirog/mcp-light-memory. If the tool is not cloned yet, clone it to a stable location outside the project; if it already exists, run git pull --ff-only. Run install.py with TARGET_PROJECT=C:\Projects\App, --client opencode, and --global. --global means the global OpenCode client configuration, while the server must still be bound only to C:\Projects\App; do not use the multi-project router. If the installer returns MCP REGISTRATION: MANUAL_REQUIRED, do not report success and follow the safe JSONC instructions. After real registration, verify from cwd=C:\Projects\App: mlm.py --version, mlm.py status, and mlm.py guard, and confirm that the global OpenCode configuration contains mcp-light-memory and the C:\Projects\App path.
For OpenCode 2 / V2, use the same prompts but explicitly say OpenCode 2 / V2 and require --client opencode2. More variants: docs/ZERO-SHOT-SETUP-PROMPTS.md.
Warp reads MCP server configs from ~/.warp/.mcp.json (global, auto-spawns) or
{repo}/.warp/.mcp.json (project, requires a manual toggle per Warp docs).
Shape: mcpServers.<name> with command, args, working_directory (always set it — the memory store is resolved from it). See examples/warp.example.json and docs/WARP-SETUP.md.
OpenCode reads opencode.json/.jsonc in the project root, or
~/.config/opencode/opencode.json globally. V1 servers are flat under
mcp.<name> (no servers sub-key) with enabled: true and command as an
array — see examples/opencode-legacy.example.json and docs/OPENCODE.md.
Same config files, different shape: mcp.servers.<name>, command as an
array, and no enabled field (V2 disables via disabled: true) — see
examples/opencode-v2.example.jsonc and docs/OPENCODE.md.
PyCharm does NOT auto-read any MCP config file. The installer prints
ready-to-paste JSON + Working Directory; you add the server in
Settings → Tools → AI Assistant → MCP (STDIO) and choose Server level =
Project or Global. See examples/jetbrains.example.json.
One MCP connection in front of many projects — registry allowlist, write:false hard boundary, per-call subprocess isolation.
projects.json){
"projects": {
"backend": { "root": "/abs/path/backend", "write": true },
"shared-lib": { "root": "/abs/path/shared-lib", "write": false }
}
}
{
"mcpServers": {
"mcp-light-memory-router": {
"command": "python3",
"args": ["/abs/path/mcp-light-memory/.agents/skills/internal-rag/irag_mcp_router.py", "--registry", "/abs/path/projects.json"],
"working_directory": "/abs/path/mcp-light-memory"
}
}
}
See docs/MCP-MULTI-PROJECT.md for details.
context --task "current task"
↓
recovery, if required (RECOVERY REQUIRED)
↓
checkpoint before first change
↓
implementation
↓
checkpoint after each milestone
↓
guard before finishing
Core commands (CLI alias: mlm.py or legacy irag.py):
mlm.py context --task "..."
mlm.py checkpoint --reason "..."
mlm.py search --query "..." --limit 8
mlm.py remember --type decision --title "..." --body "..."
mlm.py show <ref>
mlm.py update <ref> --status superseded
mlm.py status
mlm.py guard
mlm.py validate
mlm.py doctor
The on-disk folder INTERNAL_RAG/ and the skill directory .agents/skills/internal-rag/ are intentionally kept under their legacy names for zero-migration backward compatibility. See docs/MIGRATION-TO-MCP-LIGHT-MEMORY.md.
remember --type decision --title "..." --body "..." --tags "a,b" --evidence "src/x.py:42" --links "decisions/other.md"
show <path-or-id>
show <ref> --section Knowledge
update <ref> --add-tags "new" --append "New evidence: ..."
supersede <ref> --by <new> --reason "..."
forget <ref> # archives, does not delete
link --from <ref> --to <ref>
timeline --limit 20
status
history
Types: decision, knowledge, constraint, gotcha, failure, hypothesis, session.
mlm.py push --task "interrupted work" --reason "user-priority"
mlm.py tasks
mlm.py resume
mlm.py forget-task <id> # drop a specific task
mlm.py forget-task # clear the whole stack
.irag.yml, optional)retrieval:
limit: 10
mmr_lambda: 0.4
min_score: 0.3
embeddings: auto # auto | on | off
profile: english-fast # english-fast (default) | multilingual (PL/EN projects)
embeddings_model: null # explicit model overrides the profile
tokens:
context_budget: 5000
checkpoints:
auto_archive_sessions: true
max_task_stack: 24
mlm.py config shows the effective configuration. mlm.py config --init writes a template.
pip install -r requirements-optional.txt
When the package is available and .irag.yml has embeddings: auto (default), retrieval uses embeddings with fallback to BM25. Override at runtime with --embeddings on|off|auto.
Two retrieval profiles (see docs/EMBEDDINGS.md):
english-fast (default, all-MiniLM-L6-v2)multilingual (intfloat/multilingual-e5-small) — for Polish-English projectspython pack.py --with-embeddings --profile english-fast
# -> internal-rag-offline-1.8.1.zip (name from pack.py; 1.8.1 = VERSION file)
# On the air-gapped machine:
unzip internal-rag-offline-*.zip -d internal-rag-offline
pip install --no-index --find-links wheels/ -r requirements-optional.txt
python install.py "/path/to/project" --client <warp|opencode|opencode2|jetbrains>
See docs/OFFLINE.md for details.
The default install mode is local-only. The installer uses .git/info/exclude, not the project's .gitignore, so local memory and integration files are not accidentally committed.
Before publishing a project:
python .\privacy_check.py "D:\path\to\project"
Expected: RESULT: PASS
python .\uninstall.py "D:\path\to\project"
The uninstaller creates a backup outside the repository, then removes INTERNAL_RAG and its integrations. Use --keep-memory to preserve the memory data.
project/
├── AGENTS.md
├── .irag.yml # optional config
├── INTERNAL_RAG/
│ ├── WORKING_STATE.md
│ ├── INDEX.md
│ ├── .checkpoint.json
│ ├── decisions/ knowledge/ gotchas/ failures/ hypotheses/ sessions/ archive/
│ └── exports/
├── .agents/skills/internal-rag/
│ ├── SKILL.md
│ ├── mlm.py # primary CLI (forwards to irag.py)
│ ├── irag.py # core (legacy alias, still the canonical module)
│ ├── irag_embeddings.py # optional plugin
│ └── irag_hooks.py # optional git hooks
└── .opencode/ # OpenCode integration (optional)
Memory can be stale. Code takes precedence.
MIT.
--client jetbrains no longer writes a fake config file (PyCharm ignores MCP config files). Prints ready-to-paste JSON + IDE menu instructions instead.--unregister --client jetbrains prints a reminder to remove in the IDE UI.working_directory as a hint + prints WARNING with exact path to set in Settings → Tools → AI Assistant → MCP.Memory store: <path> printed in install output for immediate verification.detect_python() rejects the WindowsApps 0-byte stub; prefers py -0p; verifies each candidate with --version.--version immediately after writing the config and reports PASS/FAIL.--unregister deletes empty config files + parent dirs (fixes dead .warp/.mcp.json skeleton → GUARD STALE).internal-rag to MCP Light Memory (mcp-light-memory). New CLI alias mlm (mlm.py). Logo/icon assets. Migration doc. GitHub rebrand checklist.irag.py, INTERNAL_RAG/, old MCP server names preserved as deprecated aliases.trust: untrusted + security_flags. Evidence freshness (ADR-016): evidence_state. Scale benchmark (100/1k/10k). Router security regressions (+12 tests). Docs consistency test. 249 tests pass.2026-07-28 dual-era (server/discover, _meta, structuredContent, outputSchema). Registry strict write. Sources in chunk prefix. Adaptive retrieval. Link-aware context. consolidate --prepare. Router latency benchmark. ADR-010…016.--meta). FTS5 candidate prefilter. Multi-project MCP router. MCP protocol hardening (pure stdout, SDK-verified). 168 tests.valid_from/valid_to/supersedes/--at). consolidate --dry-run.index --vacuum/--embed-missing.Local-first persistent memory for coding agents and MCP clients.
{ "mcpServers": { "io.github.peterpirog-mcp-light-memory": { "command": "mcpb", "args": [ "https://github.com/PeterPirog/mcp-light-memory/releases/download/v1.8.1/mcp-light-memory-1.8.1.mcpb" ] } }}Tool
Belum ada daftar tool. Server remote mendapatkannya setelah pemeriksaan kesehatan pertama.
FAQ
Salin konfigurasi stdio untuk Cursor, Claude Desktop, Claude Code, atau VS Code di halaman ini. Konfigurasi ini memakai instalasi dari penerbit, bukan proxy PlugMCP.
Tidak ada variabel lingkungan wajib yang tercantum di catatan ini.
MCP Light Memory berjalan secara lokal melalui stdio.
Terakhir diperiksa 2026-11-09. Local-first persistent memory for coding agents and MCP clients.