RepoRadar
Leave a Tip
Item detail

Filippo-Venturini/ctxvault

CtxVault is an MIT-licensed, local-first memory infrastructure for AI agents that organizes memory into typed vaults (semantic vault for documents/knowledge, skill vault for natural-language procedures) with structural isolation enforced by the architecture rather than config. The CLI exposes vault inspection/query/write, the HTTP API lets LangChain/LangGraph/custom pipelines talk to vaults via RE

Open source →Back to radar
Score7.6
Popularity65.0
Risknone
TierSilver
Score breakdown
Usefulness7.0
Novelty8.0
Momentum7.0
Maturity6.9
Open-source/build8.4
Evidence7.2
Workflow potential9.1
Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for agent developers tired of one undifferentiated vector index holding facts and procedures together. Install via `pip install ctxvault`, declare one semantic vault per agent + one skill vault per role, point Claude Desktop or any MCP client at it, and let the agent read knowledge from one vault and behavioral procedures from another without them bleeding into each other.

Who should use it

agent developers tired of one undifferentiated vector index holding facts and procedures togetherteams who want one semantic vault (knowledge) and one skill vault (procedures) per agent, structurally isolatedLangChain / LangGraph users who want a REST API into typed agent memory without writing the storage layerClaude Desktop / MCP-client users who want direct vault access via the bundled MCP server (no integration code)developers who want local-first agent memory with no cloud, no telemetry, and no external services

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

No inherent user-impacting risk is flagged from the captured evidence.

Evidence links

Closest alternatives / related signals

agent-memorytyped-memorylocal-firstmcpchromadblangchainclaude-desktopvector-database