Agent memory

A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

• Agent memory
• Books

A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

• Agent memory

A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.

• Agent frameworks
• Agent memory

A persistent, cross-tool memory layer for AI coding assistants such as Claude Code, Cursor, OpenCode and Windsurf, reached through the Model Context Protocol and backed by a shared Supabase pgvector database.

• MCP servers
• Agent memory

A durable, tenant- and dataset-isolated memory engine for autonomous AI agents, with a compatibility runtime that stores raw memories and an in-development release that adds source provenance, validation and combined SQL, vector and graph storage.

• Agent memory
• Databases

Agent memory built on a developer's own PostgreSQL and pgvector, where every retrieved result carries a verdict, a confidence score and provenance, and a query that cannot clear a calibrated trust threshold is refused instead of answered from the nearest match.

• Agent memory
• RAG

A normalized store of work context that AI accumulates and maintains on its own, injecting a company's product, code and decision history into every team member's AI so everyone works from the same context.

• Agent memory

An MCP server that gives AI coding agents memory that survives between sessions, through persistent task tracking, versioned docs and semantic code search over a tree-sitter-based index.

• Agent memory

A portable memory layer that gives any AI system -- assistants, agents, robots, vehicles or code -- persistent recall across sessions, devices, users and teams, and checks its actions against rules the user set.

• Agent memory

A local-first knowledge base with semantic search built for AI coding assistants, so they can query project knowledge directly instead of re-scanning files or being re-explained the codebase every session.

• Agent memory

A self-hosted, durable memory and retrieval layer for AI agents and apps, combining vector, keyword, temporal and graph recall over your own Qdrant and Memgraph.

• Agent memory

A biomimetic, symbolic cognitive memory architecture for AI agents that gives them persistent cross-session memory using neurobiology-inspired structures and linear algebra instead of dense embeddings.

• Agent memory

An open-source spatial AI memory system that stores agent memories as tetrahedrons in 3D space, builds a knowledge graph from them, and serves persistent cross-session memory to AI agents over MCP.

• Agent memory

A local sidecar that turns an AI agent's completed execution traces into reviewed memories, reusable skills and evidence-backed training data, gating every proposed change behind human review instead of silently mutating agent state.

• Agent memory
• AI evals

A private AI assistant and local runtime that runs entirely on the user's own hardware: it holds conversations by voice or text, controls the desktop, reads the screen, writes code, and builds a private model of the user over time.

• Agent frameworks
• Agent memory
• Speech

An experimental local background service that watches a project's repositories and compiles their changing state into a compact context artifact an AI assistant can read directly.

• Agent memory

A self-hosted MCP server that turns an existing Obsidian or plain Markdown vault into searchable, durable memory for Claude Code, Codex, Cursor and other MCP-capable agents, with sourced, hybrid retrieval over a governed corpus.

• MCP servers
• Agent memory

A tool that indexes a TypeScript codebase into a Neo4j code knowledge graph, so Claude Code and other AI coding agents can answer architecture questions in Cypher instead of relying on embedding similarity over code chunks.

• MCP servers
• Agent memory

A local-first CLI that packs a codebase into a compact, lossless, searchable archive that can be queried and restored byte-for-byte, for agent memory and local RAG.

• Agent memory
• RAG

A research paper and accompanying code that stores a user's facts as a few rows in a content-addressed edit to a language model's parameters, instead of a separate retrieval index or per-user LoRA.

• Agent memory
• Papers

A local, API-free Claude Code plugin that gives the agent four layers of long-term memory — conversation, atom, scene and persona — built on local full-text and vector search.

• Agent memory

A local-first C# library for building long-term memory into .NET AI agents, assistants, simulations and robots, combining semantic retrieval, an auditable temporal history and spatial memory of timestamped 3D observations.

• Agent memory

A local-first memory tool that compiles Codex and Claude Code session history into an auditable, plain-Markdown wiki so coding agents can recall past investigations, decisions and failures instead of repeating them, without a vector database.

• Agent memory

A local-first memory library for AI agents that stores everything in one SQLite file with no required dependencies, combining exact vector and BM25 recall, conflict detection and a time-travel history, with LangChain, CrewAI and MCP integrations.

• Agent memory