Cozo Memory
Local-first memory system for AI agents with hybrid search and graph reasoning
Connector by tobs-code · GitHub account verified by the MCP Registry
Chalk Labs
Need help deploying Cozo 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/tobs-code-cozo-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 and install config. Checked Oct 25, 2026.
- Tools
- 2 read · 3 write · 0 delete
- Secrets
- None asked for
- Install scripts
- Not scanned yet
- Runs as
- Node.js 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.
analyze_graphquery_memory
Write 3 · Create, change, send or run things.
edit_user_profilemanage_systemmutate_memory
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+…].
analyze_graphGraph analysis and advanced retrieval strategies. Select operation via 'action'. Common operations: explore (navigate/find paths), communities (detect groups), pagerank (entity importance), shortest_path Advanced: semantic_walk, infer_relations, bridge_discovery, hnsw_clusters, temporal patterns Use 'explore' without end_entity for neighborhood, with end_entity for shortest path. For detailed action descriptions and parameters, see docs/USAGE-GUIDE.md.
edit_user_profileDirect management of the global user profile ('global_user_profile'). Edit user preferences, work style, and profile metadata. The user profile is automatically boosted in all searches (50% score boost). Parameters: name, type, metadata, observations (array), clear_observations (boolean) Example: { observations: [{ text: "Prefers TypeScript over JavaScript" }] } Note: Use mutate_memory with action='add_observation' and entity_id='global_user_profile' for implicit updates.
manage_systemSystem maintenance and memory management. Select operation via 'action'. Monitoring: health (status check), metrics (detailed stats) Data portability: export_memory (JSON/Markdown/Obsidian), import_memory (Mem0/MemGPT/Cozo) Backups: snapshot_create, snapshot_list, snapshot_diff Optimization: cleanup (LLM consolidation), defrag (merge duplicates), reflect (find contradictions) Advanced: summarize_communities, compress_memory_levels, analyze_memory_distribution, compact, list_inference_rules, delete_inference_rule Important: Use confirm=false for dry-run before cleanup/defrag. clear_memory req…
mutate_memoryWrite access to memory. Select operation via 'action'. Common actions: create_entity, add_observation, create_relation, update_entity, delete_entity Advanced: run_transaction, add_inference_rule, ingest_file, session/task management, conflict detection Use entity_id='global_user_profile' for storing persistent user preferences (automatically boosted in searches). For detailed action descriptions, parameters, and examples, see docs/USAGE-GUIDE.md. Note: Inference rules must return exactly 5 columns: [from_id, to_id, relation_type, confidence, reason]. Invalid syntax will result in errors.
query_memoryRead access to memory with multiple retrieval strategies. Use 'search' for quick lookups, 'adaptive_retrieval' for auto-optimization, or 'context' for comprehensive exploration. Available actions: - search, advancedSearch: Hybrid search with query (required) - context: Context retrieval with query (required) - entity_details, history: Entity info with entity_id (required) - graph_rag, graph_walking: Graph traversal with query (required) - adaptive_retrieval, dynamic_fusion, agentic_search: Advanced search with query (required) - spreading_activation, qafd_search, hierarchical_memory_query: S…
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit
- Jun 8, 2026 (4 months ago)
- Last release
- Feb 28, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Registry name
io.github.tobs-code/cozo-memory- Version
- 1.0.3
- Auth
- No auth
- Packages
- npm cozo-memory
- License
- Apache-2.0
- Repository
- github.com/tobs-code/cozo-memory
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 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 Cozo 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
Cozo Memory MCP server. Agent Mart. https://agentmart.dev/connectors/tobs-code-cozo-memory (last updated 2026-10-24)