{"id":"yoloshii-clawmem","name":"ClawMem","homepage":null,"repo_url":"https://github.com/yoloshii/ClawMem","category":"ai-ml","subcategories":[],"tags":["ai-agent-memory","rag","mcp-server","claude-code","openclaw","sqlite","local-first","typescript","bun","vector-search","hybrid-search"],"what_it_does":"ClawMem is a local-first context engine/memory for AI coding agents. It indexes markdown/project documents into a SQLite-based “vault”, performs hybrid retrieval (BM25 + vector + reranking + graph/intent-based traversal), and integrates with Claude Code via hooks + an MCP stdio server and with OpenClaw via a ContextEngine plugin or MCP tools. It also captures session decisions/handoffs and writes them back to the same local vault; it includes measures against prompt injection in surfaced content and supports deduplication, lifecycle (pin/snooze/archive), and crash-safe transaction-safe indexing.","use_cases":["Persistent coding agent memory for Claude Code and OpenClaw across sessions/projects","Retrieval-augmented grounding over local markdown notes, docs, and research dumps","Session decision capture and handoff generation for long-running coding workflows","Targeted retrieval via MCP tools (timeline, causal links, intent search) when hooks don’t surface enough context","Local-only “hybrid RAG + memory graph” for privacy-sensitive developer teams"],"not_for":["Use as a hosted/cloud service for remote memory (it is explicitly local/no cloud dependencies)","Use in environments where Bun/system dependencies cannot be installed","Multi-tenant server deployments without strong additional isolation controls (primarily designed for local single-user vaults)","Environments needing a public REST/GraphQL API for external systems (no such interface is described)"],"best_when":"You want an on-device, agent-integrated memory layer that can surface relevant context automatically and also provide tool-based retrieval (MCP/OpenClaw) while keeping data local in a SQLite vault.","avoid_when":"You need a centralized, network-accessible API or require robust multi-user authentication/authorization at the service layer.","alternatives":["Local vector/RAG tools and agents’ built-in memory (e.g., generic embeddings + vector DB + prompt augmentation)","Other local context engines / RAG frameworks that expose REST APIs or run as separate services","Open source note-search + embeddings pipelines without agent-specific lifecycle hooks"],"af_score":62.8,"security_score":48.8,"reliability_score":42.5,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T15:22:48.049794+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":true,"sdk_languages":["TypeScript","JavaScript"],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["Local stdio MCP server (no user auth described)","Local plugin integration (no user auth described)"],"oauth":false,"scopes":false,"notes":"No authentication mechanism for MCP or local tools is described; the primary security model appears to be local execution and filesystem/vault isolation."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Open-source (MIT). Costs are primarily compute/storage for local indexing and optional model servers (llama.cpp), not service pricing."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":["Local machine filesystem (SQLite vault)"],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":62.8,"security_score":48.8,"reliability_score":42.5,"mcp_server_quality":65.0,"documentation_accuracy":70.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":95.0,"rate_limit_clarity":5.0,"tls_enforcement":100.0,"auth_strength":10.0,"scope_granularity":20.0,"dependency_hygiene":55.0,"secret_handling":70.0,"security_notes":"Local-first design with no API keys/cloud dependencies reduces exposure. However, no explicit authN/authZ is described for MCP/local tools; therefore security relies on local host trust and vault filesystem permissions. The README claims “guards against prompt injection” for surfaced content and mentions transaction-safe indexing and crash-safe behavior, which can reduce certain integrity risks. Dependency hygiene is not verifiable from provided manifest/README; scores are estimated based on explicit dependencies without CVE review.","uptime_documented":0.0,"version_stability":55.0,"breaking_changes_history":45.0,"error_recovery":70.0,"idempotency_support":"true","idempotency_notes":"Indexing is described as transaction-safe/atomic with rollback, and there is deduplication for hook-generated observations within a window; these imply resilience to repeated operations, though explicit idempotency semantics for every MCP tool are not detailed.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Designed as a local system; agents must run where the vault/models exist.","No authentication for MCP tools is described; in practice, ensure only trusted local clients can connect.","Integration modes share the same SQLite vault—concurrent access exists (WAL + busy_timeout mentioned) but agent workloads that heavily parallelize may still contend.","“Hooks handle 90%” suggests relying purely on MCP may miss lifecycle orchestration such as compaction and afterTurn/feedback-loop flows unless using the OpenClaw ContextEngine plugin."]}}