Provena — AI skill for Claude Code
Self-hosted memory for AI agents via MCP.
How to install Provena
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open admiralpunk/Provena and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Provena does
Self-hosted memory for AI agents via MCP. Capture source events, retrieve context across sessions, and explain evidence-backed claims.
Alternatives in AI
- Nodeterm — Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as dragga 1.3k ★
- Academic Humanizer — Strip AI-writing tells from papers and grant proposals (NSF/NIH), while keeping scholarly voice and tying clai 1.1k ★
- OpenContext — A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC 1.1k ★
README
Provena
Evidence-backed memory for AI agents.
Know what an agent remembers—and why.
Provena is an open-source, self-hosted memory service for AI agents. Its MCP connector gives Codex, Claude Code, Gemini CLI, and other clients context across sessions. Each claim stays linked to its source event, review status, and scope, so you can inspect what an agent remembers and why.
Product demo
Watch a walkthrough of setup, cross-session recall, and the operator console:
https://github.com/user-attachments/assets/37fe219c-b678-4c6d-811d-bfdd37552628
Why provenance matters
An agent can retrieve a relevant fact that is wrong, stale, or taken from an untrusted source. Provena keeps the original evidence and the derived memory separate:
Event: Alex says, "Pineapple on pizza is a crime."
Claim: Alex dislikes pineapple on pizza.
Evidence: The claim links to Alex's original words.
Later event: Alex says, "I tried it. I owe pineapple an apology."
Updated claim: Alex likes pineapple on pizza.
Provena keeps both statements, so it can explain why Alex's preference changed. Events and evidence are append-only. Claims have review status, optional validity time, and exact tenant and project or branch scope. Model-extracted claims remain candidates; source authority is separate from search relevance and never grants permission to act. `memory_explain` traces a claim back to its source, review history, conflicts, and recorded retrievals.
Provena is one FastAPI service backed by PostgreSQL and pgvector. MCP and host hooks capture turns and retrieve attributed context; Ollama or an optional hosted model extracts candidate facts and embeddings. The Next.js co
Related Skills
Recollect
Self-hosted AI memory and MCP coordination for coding agents. Persistent context across repositories and sessi
Hexis
Git-backed control plane for AI-agent skills, tools, context, permissions, and identity. Self-hosted and MCP-n
Context Memory Manager
CMM — Context Memory Manager: a self-hosted, offline file manager for the memory folders and prompts of AI too
Aeon Agent Harness
Self-hosted agent harness platform: durable Temporal execution, typed context/evidence, policy enforcement out
Cemainou
The work log your team's AI agents write. A self-hosted web app plus an MCP server: daily updates drafted from
ExternalBrain
Self-improving, self-hosted memory across every AI coding tool, project, and team (Claude Code, Cursor, Copilo
Related Agents
Firecrawl Scraper
Web scraping and research subagent. Dispatched to scrape URLs, search the web, crawl sites, and extract struct
Memory Guard
Use when artifact-backed memory claims need auditing before reliance or at session close. Not when recording c
Context Optimizer
Meta utility agent for token and context optimization. Spawn when needing to compress agent prompts, optimize