Compound Memory
Local-first shared memory for multiple AI agents that compounds with use; Markdown + git, MCP + CLI.
Connector by chinwe · GitHub account verified by the MCP Registry
Chalk Labs
Need help deploying Compound Memory?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/chinwe-compound-memory
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.
- Tools
- 2 read · 2 write · 0 delete · 1 not yet classified
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Tools by what they do 5
Read from the source code; the running server may list different tools.
Read 2 · Look things up without changing anything.
memory_getmemory_search
Write 2 · Create, change, send or run things.
memory_linkmemory_write
Not yet classified 1 · We could not tell from the name and description.
memory_feedback
Secrets and settings it asks for
Other settings (environment variables or headers).
COMPOUND_MEMORY_AGENT_IDCOMPOUND_MEMORY_ROOT
Network hosts it talks to 1
github.com· found in code
Files it touches
~/.claude/projects- Your home directory (~)
~/.dsh/sessions~/.workbuddy/projects~/.zcode/cli/db/db.sqlite- Any path the agent passes to its tools
Tools (5)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
memory_feedbackReport feedback on a memory with an outcome (closes the compounding loop — call after actually adopting a memory). Every outcome advances uses and last_used. outcome: 'success' (default, the memory worked), 'failure' (it misled you — confidence drops 0.2, floor 0.05), 'contradiction' (you dispute it — confidence frozen and a review entry is queued pending adjudication), 'obsolete' (it is superseded — archived immediately), 'unknown' (records the event only: confidence does not move). Anything else is rejected. Success raises confidence (+0.1; extra +0.15 when a different agent validates for th…
memory_getFetch a memory by id; one-hop link neighbors are included by default. reader: your own source agent id — required when the memory lives in a private 'agent-<name>' namespace (readable only by its owner host). project: your workspace project slug — get-by-id itself is always readable regardless of project, but embedded neighbors are filtered to global ones plus your project's. After adopting it, call memory_feedback (agent = your source id).
memory_linkCreate a bidirectional link between two memories (compounding source #2: association). Both memories must live in the same namespace; cross-namespace links are rejected. Memories in a private 'agent-<name>' namespace accept links only from the owner (agent = your own source agent id).
memory_searchSearch memories. Fuses lexical (BM25) and, when the vec extra + model are installed, vector (BGE) recall via RRF; otherwise falls back to lexical only. The response always includes `retrieval` `{mode, reason}`: mode is `vector` or `lexical`, and reason is set when the vector channel is off or the last recall failed (embedder-unavailable, engine-unavailable, or degraded) so a lexical-only fallback is visible without a separate tool. Each hit's 'similarity' field carries the normalized RRF fusion score (fused/rrf_max) in dual-channel mode, or the normalized BM25 score in lexical-only (linear) mo…
memory_writeDescription is built at runtime.
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Weekly downloads
- 474
- Last commit
- Oct 22, 2026 (9 days ago)
- Last release
- Oct 25, 2026 (6 days ago)
- Last package publish
- Oct 22, 2026 (9 days ago)
From GitHub (fetched Oct 24, 2026) and the package registry.
Details
- Registry name
io.github.chinwe/compound-memory- Version
- 0.5.11
- Auth
- No auth
- Packages
- pypi compound-memory
- License
- MIT
- Repository
- github.com/chinwe/compound-memory
- First seen
- Oct 24, 2026
- Last checked
- Oct 25, 2026
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Compound Memory running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Compound Memory MCP server. Agent Mart. https://agentmart.dev/connectors/chinwe-compound-memory (last updated 2026-10-25)