Pensyve
This exposes episodic, semantic, and procedural memory for AI agents through MCP tools like `recall`, `remember`, `episode_start`, and `consolidate`. It runs offline first with SQLite and ONNX embeddings, scales to Postgres with pgvector, and uses an 8-signal fusion retrieval system that combines vector search, BM25, graph traversal, recency, frequency, and confidence scoring. Memories fade via FSRS forgetting curves and get promoted from episodic to semantic through consolidation. Reach for this when you need agent memory that persists across sessions and surfaces the right context without manual session management. It ships Python, TypeScript, and Go SDKs alongside the MCP server, plus framework adapters for LangChain, CrewAI, and AutoGen.
- GitHub stars
- 99
- tools
- 4
- transport
- STDIO
- last updated
- Oct 1, 2026
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
pensyve_rememberThe server provides tools such as pensyve_remember, pensyve_recall, pensyve_observe, and pensyve_inspect.
The server provides tools such as pensyve_remember, pensyve_recall, pensyve_observe, and pensyve_inspect.
No parameter schema in public metadata yet.
pensyve_recallThe server provides tools such as pensyve_remember, pensyve_recall, pensyve_observe, and pensyve_inspect.
The server provides tools such as pensyve_remember, pensyve_recall, pensyve_observe, and pensyve_inspect.
No parameter schema in public metadata yet.
pensyve_observeThe server provides tools such as pensyve_remember, pensyve_recall, pensyve_observe, and pensyve_inspect.
The server provides tools such as pensyve_remember, pensyve_recall, pensyve_observe, and pensyve_inspect.
No parameter schema in public metadata yet.
pensyve_inspectThe server provides tools such as pensyve_remember, pensyve_recall, pensyve_observe, and pensyve_inspect.
The server provides tools such as pensyve_remember, pensyve_recall, pensyve_observe, and pensyve_inspect.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Pensyve logo
Pensyve
Pensyve is an open-source runtime for persistent AI agent memory. It stores facts, conversations, observations, and action outcomes so an agent can retrieve them in later sessions. You can use it through Python, a Model Context Protocol (MCP) server, a command-line tool, or a REST API.
The Rust engine uses SQLite for local storage and runs embedding models locally to search by meaning. TypeScript and Go clients connect to a gateway you run yourself. Local use does not require a Pensyve account or API key. Your application or client integration calls Pensyve to save and retrieve memories.
Choose a setup
Details
- Repository
- github.com/major7apps/pensyve
- Website
- github.com/major7apps/pensyve
- Category
- AI & LLM Tools
- Package
ghcr.io/major7apps/pensyve-mcp:5.0.0- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
emem, the verifiable memory protocol for the physical worldvortx-ai/ememShared, verifiable memory for machines and AI. Encode where data lives; decode with any AI.89stars
Sverklosverklo/sverkloLocal-first MCP code intelligence: 37 tools — hybrid search, blast-radius, diff review, memory.71stars
Token Enhancerxelektron/token-enhancerCuts AI web-fetching costs up to 99.9% by stripping page junk before it reaches your LLM.66stars
Threadline Mcpsagemindai/instarAgent-to-agent messaging relay. Discover agents, send messages, and receive replies. Zero-config.0stars
Three.js DevTools MCPdmitriygolub/threejs-devtools-mcpInspect and edit Three.js scenes, materials, shaders, lights in real time from any AI agent64stars
Zikkaronamanhij/zikkaronBiologically-inspired persistent memory engine for Claude Code MCP agents60stars