Memory & State

Gives existing agent harnesses a self-hosted memory and skills layer with sourced facts, hybrid search, and cited synth…

Runs a self-improving personal agent from a terminal TUI or a Telegram/Discord/Slack gateway, creating its own skills,…

Stores and searches multimodal vectors in an embedded database built on the Lance columnar format, running in-process o…

Builds a graph-based retrieval index over documents so agents can answer questions spanning many sources, served throug…

Records your screen and audio 24/7 locally, then serves that history as searchable context to Claude, Codex and other c…

Give a team of agents shared long-term memory — turns conversations, docs, and code into governed Chat Memory, Skill, L…

Gives coding agents such as Claude Code, Codex, Cursor, and Gemini CLI a shared local memory server that captures sessi…

Compiles a company-wide wiki from Slack, files, wikis, and repos, then gives agents its own computer plus MCP search ov…

Stores issues and agent memory as a dependency graph so coding agents keep durable working context and track outstandin…

Captures Claude Code tool usage as searchable observations and replays summarized context into new sessions, giving cod…

Compresses LLM context such as code, JSON, logs, and chat history through a reversible 14-stage pipeline with no LLM ca…

Query a multi-language codebase as a knowledge graph — parse repositories into function, class, and dependency relation…

Turns your coding-agent conversations into a local-first codebase wiki, capturing architectural decisions and instituti…

Indexes repositories into a persistent tree-sitter knowledge graph of functions, classes, call chains, and HTTP routes,…

Builds queryable memory for agents by turning documents and conversations into a knowledge graph plus vector store, sel…

Keeps raw tool output out of coding agents' context by running code and commands in a sandbox, indexing results for sea…

Runs a self-hosted personal agent that plans multi-step tasks, calls built-in and MCP tools, installs skills, and answe…

Gives agents a local-first memory layer that stores conversations, files and trajectories as Markdown, indexes them in…

Give coding agents durable memory of past sessions — a local-first layer combining vector and BM25 search over prior co…

Builds a local, always-fresh graph of your codebase as linked markdown and serves it to coding agents over MCP and a CL…

Maps a codebase, docs, PDFs, and media into a queryable knowledge graph so AI coding assistants trace and cite paths in…

Builds temporally aware knowledge graphs for agents in real time, tracking when each fact became true so memory reflect…

Gives agents a self-hosted long-term memory server that retains facts, recalls them with parallel semantic, keyword, gr…

User state management platform for AI apps. Stores user context, preferences, and interaction history to enable persona…

Stateful agent framework with built-in memory. Agents persist context between sessions via structured memory blocks. Fo…

Builds and maintains an interlinked wiki from your documents in a desktop app, and exposes hybrid search, graph and fil…

Public, persistent message board for AI agents to publish and read findings across sessions via HTML/JSON and an HTTP A…

Persistent memory layer for AI agents and LLMs. Stores, searches, and retrieves user and session memories across framew…

Runs a self-hosted personal AI agent from a WebUI, terminal, or chat apps, combining tools, long-term memory, MCP serve…

Turns a Notion workspace into an agent-neutral skills library, serving spec-compliant skill files over an API with an o…

Compiles what you and your coding agent learn into a linked Obsidian markdown wiki through agent skills, a CLI, and an…

Store coding-agent memory in git — an embedded MCP server with sub-millisecond BM25 search, written in pure Go with no…

Runs an open-source agent harness with a Rust core as a desktop app, browser UI, terminal client or embeddable library,…

Serves agent memories, resources and skills as a virtual filesystem under viking:// URIs, loading context on demand acr…

Shared knowledge layer that lets multiple agents read and write to a common memory, so context learned by one agent is…

Gives AI agents a hosted runtime for shared error-to-fix evolution, persistent memory, compressed web context, and agen…

Official Redis MCP server for agentic applications to read, write, and search Redis data structures including JSON, has…

Indexes a codebase's graph, git history, docs, and decisions locally and serves ten MCP tools plus a dashboard, so codi…

Builds a backlinked knowledge graph from your email, meetings and Slack in a local desktop app, then lets agents query…

Open-source self-hosted memory layer for AI agents. Gives any agent persistent, semantic memory across sessions — model…

Memory API for AI applications. Store and retrieve user memories, bookmarks, and knowledge with semantic search. One un…

Manages Markdown knowledge bases as Git-backed vaults in a desktop app, and lets coding agents search, read and edit no…

Long-term memory store for AI assistants. Extracts and indexes facts, entities, and summaries from conversations. Fast…