A community-driven registry for Claude, Cursor, Windsurf, Cline & more. Not affiliated with Anthropic.
Are you the author? Sign in to claim
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex), backed by Markdown and Milvus.
memsearch
Cross-platform semantic memory for AI coding agents.
PROJECT.md and USER.md notes current across sessions. See Advanced Memory Maintenance..md files — human-readable, editable, version-controllable. Milvus is a "shadow index": a derived, rebuildable cachePick your platform, install the plugin, and you're done. Each plugin captures conversations automatically and provides semantic recall with zero configuration.
# Install
/plugin marketplace add zilliztech/memsearch
/plugin install memsearch
# Restart Claude Code to activate the plugin
After restarting, just chat with Claude Code as usual. The plugin captures every conversation turn automatically.
Verify it's working — after a few conversations, check your memory files:
ls .memsearch/memory/ # you should see daily .md files
cat .memsearch/memory/$(date +%Y-%m-%d).md
Recall memories — two ways to trigger:
/memory-recall what did we discuss about Redis?
Or just ask naturally — Claude auto-invokes the skill when it senses the question needs history:
We discussed Redis caching before, what was the TTL we chose?
# Install
git clone --depth 1 https://github.com/zilliztech/memsearch.git
bash memsearch/plugins/codex/scripts/install.sh
codex --yolo # needed for ONNX model network access
After installing, chat as usual. Hooks capture and summarize each turn.
Verify it's working:
ls .memsearch/memory/
Recall memories — use the skill:
$memory-recall what did we discuss about deployment?
# Install from ClawHub
openclaw plugins install --force clawhub:memsearch
openclaw config set plugins.entries.memsearch.hooks.allowConversationAccess true
openclaw config set plugins.entries.memsearch.hooks.allowPromptInjection true
openclaw gateway restart
After installing, chat in TUI as usual. The plugin captures each turn automatically.
Verify it's working — memory files are stored in your agent's workspace:
# For the main agent:
ls ~/.openclaw/workspace/.memsearch/memory/
# For other agents (e.g. work):
ls ~/.openclaw/workspace-work/.memsearch/memory/
Recall memories — two ways to trigger:
/memory-recall what was the batch size limit we set?
Or just ask naturally — the LLM auto-invokes memory tools when it senses the question needs history:
We discussed batch size limits before, what did we decide?
// In ~/.config/opencode/opencode.json
{ "plugin": ["@zilliz/memsearch-opencode"] }
After installing, chat in TUI as usual. A background daemon captures conversations.
Verify it's working:
ls .memsearch/memory/ # daily .md files appear after a few conversations
Recall memories — two ways to trigger:
/memory-recall what did we discuss about authentication?
Or just ask naturally — the LLM auto-invokes memory tools when it senses the question needs history:
We discussed the authentication flow before, what was the approach?
All plugins share the same memsearch backend. Configure once, works everywhere.
Defaults to ONNX bge-m3 — runs locally on CPU, no API key, no cost. On first launch the model (~558 MB) is downloaded from HuggingFace Hub.
memsearch config set embedding.provider onnx # default — local, free
memsearch config set embedding.provider openai # needs OPENAI_API_KEY
memsearch config set embedding.provider ollama # local, any model
All providers and models: Configuration — Embedding Provider
Just change milvus_uri (and optionally milvus_token) to switch between deployment modes:
Milvus Lite (default) — zero config, single file. Great for getting started:
# Works out of the box, no setup needed
memsearch config get milvus.uri # → ~/.memsearch/milvus.db
⭐ Zilliz Cloud (recommended) — fully managed, free tier available — sign up 👇:
memsearch config set milvus.uri "https://in03-xxx.api.gcp-us-west1.zillizcloud.com"
memsearch config set milvus.token "your-api-key"
You can sign up on Zilliz Cloud to get a free cluster and API key.
For multi-user or team environments with a dedicated Milvus instance. Requires Docker. See the official installation guide.
memsearch config set milvus.uri http://localhost:19530
📖 Full configuration guide: Configuration · Platform comparison
Each plugin keeps its native capture summarizer unless you override it explicitly:
memsearch config set plugins.codex.summarize.model gpt-5.1-codex-mini
memsearch config set plugins.opencode.summarize.model anthropic/claude-haiku
Advanced users can route plugin summarization through a memsearch-managed API provider:
memsearch config set llm.providers.openai.type openai
memsearch config set llm.providers.openai.model gpt-5-mini
memsearch config set llm.providers.openai.api_key env:OPENAI_API_KEY
memsearch config set plugins.codex.summarize.provider openai
Leave plugins.<platform>.summarize.provider empty or set it to native to preserve the default behavior. Plugin-specific summarize settings do not fall back to llm.model.
You can also disable automatic capture for a project while keeping the plugin installed:
memsearch config set plugins.codex.summarize.enabled false --project
Plugins can optionally maintain higher-level project and user notes in the background. These tasks are disabled by default and run only when a plugin wakes them after a session/turn, the journal input changed, and min_interval_hours has elapsed.
memsearch config set plugins.codex.project_review.enabled true --project
memsearch config set plugins.codex.project_review.provider native --project
memsearch config set plugins.codex.project_review.min_interval_hours 24 --project
memsearch config set plugins.codex.project_review.output_file .memsearch/PROJECT.md --project
memsearch config set plugins.codex.user_profile.enabled true --project
memsearch config set plugins.codex.user_profile.output_file .memsearch/USER.md --project
project_review summarizes durable project state such as active threads, decisions, risks, and next steps. user_profile captures reusable user preferences, working style, recurring goals, and background context. Both read .memsearch/memory by default; set input_dir if your journal files live somewhere else.
Use provider = "native" to reuse the current agent's own non-interactive model path, or point the task at a named [llm.providers.<name>] API provider. Custom prompt files can be configured with prompts.project_review and prompts.user_profile.
The memory-config skill, installed with the plugins, can inspect the current setup, explain these options, and make safe project-scoped changes from natural-language requests.
Beyond episodic journals and the semantic PROJECT.md / USER.md notes, MemSearch can grow a third memory layer — procedural memory: reusable skills distilled from the workflows you repeat. When enabled, a background pass mines recent journals for recurring multi-step procedures and writes them as candidate skills under .memsearch/skill-candidates/ (a git-tracked store that keeps evolving). Candidates are inert; turning one into an agent-visible skill is a deliberate, human step.
# Enable distillation (disabled by default, like the maintenance tasks above)
memsearch config set plugins.codex.memory_to_skill.enabled true --project
# How many times a workflow must recur before it is distilled (default 3; lower = more eager)
memsearch config set plugins.codex.memory_to_skill.min_occurrences 3 --project
# Review candidates, then install one into an agent's skill directory
memsearch skills list
memsearch skills install <name> --path .claude/skills
The /memory-to-skill skill (installed with the plugins) drives the review-and-install flow: it lists candidates, asks where to install, and copies the chosen skill into .claude/skills (Claude Code), .codex/skills (Codex), .agents/skills (OpenCode/Cursor/…), or any path you configure. Because the store keeps evolving, re-installing simply takes a fresh snapshot. The distilled SKILL.md follows the Agent Skills open standard, so a skill distilled once is portable across agents.
Beyond ready-to-use plugins, memsearch provides a complete CLI and Python API for building memory into your own agents. Whether you're adding persistent context to a custom agent, building a memory-augmented RAG pipeline, or doing harness engineering — the same core engine that powers the plugins is available as a library.
┌──────────────────────────────────────────────────────────────┐
│ 🧑💻 For Agent Users (Plugins) │
│ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌────────┐ ┌──────┐ │
│ │ Claude │ │ OpenClaw │ │ OpenCode │ │ Codex │ │ Your │ │
│ │ Code │ │ Plugin │ │ Plugin │ │ Plugin │ │ App │ │
│ └────┬─────┘ └────┬─────┘ └────┬─────┘ └───┬────┘ └──┬───┘ │
│ └─────────────┴────────────┴───────────┴────────┘ │
├────────────────────────────┬─────────────────────────────────┤
│ 🛠️ For Agent Developers │ Build your own with ↓ │
│ ┌─────────────────────────┴──────────────────────────────┐ │
│ │ memsearch CLI / Python API │ │
│ │ index · search · expand · watch · compact │ │
│ └─────────────────────────┬──────────────────────────────┘ │
│ ┌─────────────────────────┴──────────────────────────────┐ │
│ │ Core: Chunker → Embedder → Milvus │ │
│ │ Hybrid Search (BM25 + Dense + RRF) │ │
│ └────────────────────────────────────────────────────────┘ │
├──────────────────────────────────────────────────────────────┤
│ 📄 Markdown Files (Source of Truth) │
│ memory/2026-03-27.md · memory/2026-03-26.md · ... │
└──────────────────────────────────────────────────────────────┘
Plugins sit on top of the CLI/API layer. The API handles indexing, searching, and Milvus sync. Markdown files are always the source of truth — Milvus is a rebuildable shadow index. Everything below the plugin layer is what you use as an agent developer.
Capture — after each conversation turn:
User asks question → Agent responds → Stop hook fires
│
┌────────────────────┘
▼
Parse last turn
│
▼
LLM summarizes (haiku)
"- User asked about X."
"- Claude did Y."
│
▼
Append to memory/2026-03-27.md
with <!-- session:UUID --> anchor
│
▼
memsearch index → Milvus
Recall — 3-layer progressive search:
User: "What did we discuss about batch size?"
│
▼
L1 memsearch search "batch size" → ranked chunks
│ (need more?)
▼
L2 memsearch expand <chunk_hash> → full .md section
│ (need original?)
▼
L3 parse-transcript <session.jsonl> → raw dialogue
Plugins append ──→ .md files ←── human editable
│
▼
memsearch watch (live watcher)
│
detects file change
│
▼
re-chunk changed .md
│
hash each chunk (SHA-256)
│
┌───────────┴───────────┐
▼ ▼
hash unchanged? hash is new/changed?
→ skip (no API call) → embed → upsert to Milvus
│ │
└───────────┬───────────┘
▼
┌──────────────────┐
│ Milvus (shadow) │
│ always in sync │
│ rebuildable │
└──────────────────┘
# Install as a global CLI tool — recommended when you mainly use the
# `memsearch` command or any of the agent plugins (Claude Code, Codex,
# OpenClaw, OpenCode), which all shell out to the CLI.
uv tool install memsearch # via uv
pipx install memsearch # via pipx
pip install memsearch # plain pip
# Install as a project dependency — use this if you want to import
# `memsearch` from your own Python code (e.g. via the MemSearch class).
uv add memsearch # via uv, adds to pyproject.toml
pip install memsearch # into an activated venv
# As a CLI tool (recommended — local ONNX, no API key)
uv tool install "memsearch[onnx]"
pipx install "memsearch[onnx]"
pip install "memsearch[onnx]"
# As a project dependency
uv add "memsearch[onnx]"
# Other options: [openai], [google], [voyage], [jina], [mistral], [ollama], [local], [all]
from memsearch import MemSearch
mem = MemSearch(paths=["./memory"])
await mem.index() # index markdown files
results = await mem.search("Redis config", top_k=3) # semantic search
scoped = await mem.search("pricing", top_k=3, source_prefix="./memory/product")
print(results[0]["content"], results[0]["score"]) # content + similarity
import asyncio
from datetime import date
from pathlib import Path
from openai import OpenAI
from memsearch import MemSearch
MEMORY_DIR = "./memory"
llm = OpenAI() # your LLM client
mem = MemSearch(paths=[MEMORY_DIR]) # memsearch handles the rest
def save_memory(content: str):
"""Append a note to today's memory log (OpenClaw-style daily markdown)."""
p = Path(MEMORY_DIR) / f"{date.today()}.md"
p.parent.mkdir(parents=True, exist_ok=True)
with open(p, "a") as f:
f.write(f"\n{content}\n")
async def agent_chat(user_input: str) -> str:
# 1. Recall — search past memories for relevant context
memories = await mem.search(user_input, top_k=3)
context = "\n".join(f"- {m['content'][:200]}" for m in memories)
# 2. Think — call LLM with memory context
resp = llm.chat.completions.create(
model="gpt-5-mini",
messages=[
{"role": "system", "content": f"You have these memories:\n{context}"},
{"role": "user", "content": user_input},
],
)
answer = resp.choices[0].message.content
# 3. Remember — save this exchange and index it
save_memory(f"## {user_input}\n{answer}")
await mem.index()
return answer
async def main():
# Seed some knowledge
save_memory("## Team\n- Alice: frontend lead\n- Bob: backend lead")
save_memory("## Decision\nWe chose Redis for caching over Memcached.")
await mem.index() # or mem.watch() to auto-index in the background
# Agent can now recall those memories
print(await agent_chat("Who is our frontend lead?"))
print(await agent_chat("What caching solution did we pick?"))
asyncio.run(main())
pip install memsearch anthropic
import asyncio
from datetime import date
from pathlib import Path
from anthropic import Anthropic
from memsearch import MemSearch
MEMORY_DIR = "./memory"
llm = Anthropic()
mem = MemSearch(paths=[MEMORY_DIR])
def save_memory(content: str):
p = Path(MEMORY_DIR) / f"{date.today()}.md"
p.parent.mkdir(parents=True, exist_ok=True)
with open(p, "a") as f:
f.write(f"\n{content}\n")
async def agent_chat(user_input: str) -> str:
# 1. Recall
memories = await mem.search(user_input, top_k=3)
context = "\n".join(f"- {m['content'][:200]}" for m in memories)
# 2. Think — call Claude with memory context
resp = llm.messages.create(
model="claude-sonnet-4-6",
max_tokens=1024,
system=f"You have these memories:\n{context}",
messages=[{"role": "user", "content": user_input}],
)
answer = resp.content[0].text
# 3. Remember
save_memory(f"## {user_input}\n{answer}")
await mem.index()
return answer
async def main():
save_memory("## Team\n- Alice: frontend lead\n- Bob: backend lead")
await mem.index()
print(await agent_chat("Who is our frontend lead?"))
asyncio.run(main())
pip install "memsearch[ollama]"
ollama pull nomic-embed-text # embedding model
ollama pull llama3.2 # chat model
import asyncio
from datetime import date
from pathlib import Path
from ollama import chat
from memsearch import MemSearch
MEMORY_DIR = "./memory"
mem = MemSearch(paths=[MEMORY_DIR], embedding_provider="ollama")
def save_memory(content: str):
p = Path(MEMORY_DIR) / f"{date.today()}.md"
p.parent.mkdir(parents=True, exist_ok=True)
with open(p, "a") as f:
f.write(f"\n{content}\n")
async def agent_chat(user_input: str) -> str:
# 1. Recall
memories = await mem.search(user_input, top_k=3)
context = "\n".join(f"- {m['content'][:200]}" for m in memories)
# 2. Think — call Ollama locally
resp = chat(
model="llama3.2",
messages=[
{"role": "system", "content": f"You have these memories:\n{context}"},
{"role": "user", "content": user_input},
],
)
answer = resp.message.content
# 3. Remember
save_memory(f"## {user_input}\n{answer}")
await mem.index()
return answer
async def main():
save_memory("## Team\n- Alice: frontend lead\n- Bob: backend lead")
await mem.index()
print(await agent_chat("Who is our frontend lead?"))
asyncio.run(main())
📖 Full Python API reference: Python API docs
Setup:
memsearch config init # interactive setup wizard
memsearch config set embedding.provider onnx # switch embedding provider
memsearch config set milvus.uri http://localhost:19530 # switch Milvus backend
Index & Search:
memsearch index ./memory/ # index markdown files
memsearch index ./memory/ ./notes/ --force # re-embed everything
memsearch search "Redis caching" # hybrid search (BM25 + vector)
memsearch search "auth flow" --top-k 10 --json-output # JSON for scripting
memsearch expand <chunk_hash> # show full section around a chunk
Live Sync & Maintenance:
memsearch watch ./memory/ # live file watcher (auto-index on change)
memsearch compact # LLM-powered chunk summarization
memsearch stats # show indexed chunk count
memsearch reset --yes # drop all indexed data and rebuild
📖 Full CLI reference with all flags: CLI docs
Embedding and Milvus backend settings → Configuration (all platforms)
Settings priority: Built-in defaults → ~/.memsearch/config.toml → .memsearch.toml → CLI flags.
📖 Full config guide: Configuration
Bug reports, feature requests, and pull requests are welcome! See the Contributing Guide for development setup, testing, and plugin development instructions. For questions and discussions, join us on Discord.
干净、强大、属于你的 AI Agent 平台 --AI agents, without the clutter.
Pocket Flow: Codebase to Tutorial
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
Native macOS app to monitor Claude AI usage limits and watch your coding sessions live
