Let agents leave, read and tick off sticky notes in a .canvas file Obsidian can open
Runs locally- 4 tools
- Open source
- Knowledge and memory
Let agents leave, read and tick off sticky notes in a .canvas file Obsidian can open
Runs locallyOffline, citation-grounded GraphRAG over a local knowledge graph, run via Ollama
Runs locally
Persistent document knowledge for agents with hybrid search, reranking and GraphRAG
Not checked yet
Project memory for Claude Code, Cursor and Codex that retires facts when code changes
Runs locallyPersistent agent memory, behavior-based code search and bug localization
Runs locallyOffline on-device memory and filtered vector search for AI assistants
Runs locallyShared project memory in a committed file for Claude Code, Codex and Cursor sessions
Runs locallyBrowse a folder of markdown and data live, with read-only MCP tools over it
Runs locallyCrawl documentation sites into local Markdown that agents search offline
Runs locallyLook up how developers say kubectl, nginx, YAML and nearly 2,000 other terms
Runs locallyAgent memory in SQLite or Postgres that flags stale facts and abstains when unsure
Runs locallyShared memory for coding agents: proven fixes, known mistakes, skills and MCP discovery
Runs locallySearch, read and write a folder of Markdown notes with hybrid keyword and meaning search
Not checked yetTyped record store with hybrid search and RAG for AI agents, scoped per customer
Runs locallyLocal-first multilingual memory for coding agents, with verified backups and isolation
Runs locally
Encrypted, fully offline long-term memory vault shared by every agent on your computer
Runs locallyShared memory and an email address for your coding agents, via Semantik and Bud
Runs locallyLocal project memory that keeps every connected AI chat in line with your decisions
Runs locallyEncrypted agent memory you hold the key to: remember, recall, share, revoke and erase
Runs locallyLocal MCP server giving coding agents your architectural decisions, plus proposals
Runs locallyPersistent memory and a tamper-evident audit log for agents, with causal lineage
Runs locallyPrice LLM workloads, size GPUs and audit MCP configs from your coding agent
Runs locally
Read-only network config checks: drift, CIS/PCI, 802.1X, certs and change risk
Runs locally
CVSS scoring, IOC extraction, email header triage and KEV lookup for analysts
Runs locallyOne local, versioned memory shared by Claude Code, Cursor, Codex and other agents
Runs locally
Local-first shared memory layer that any MCP client can save to and recall from
Runs locallyPerfume notes, scent families and similar-scent lookups, free with no API key
Not checked yetWrites AGENTS.md, CLAUDE.md and .cursorrules from one project.faf file, locally
Runs locallyFiles client call promises by client so agents in bound folders can read the context
Runs locallyLocal MCP server for tasks and notes in a Markdown folder or Obsidian vault
Runs locallySee every kind of AI for knowledge and memory: tools, agents, MCP servers and skills.Ranked: the best AI for knowledge and memory.