
letta
AgentPlatform for stateful agents that learn from experience, with an open-source CLI harness
- Open source
- Agent framework
- 25.5K GitHub stars
- Knowledge and memory

Platform for stateful agents that learn from experience, with an open-source CLI harness
Team decision memory that serves reasons and sources to coding agents before they edit
Runs locally
Read, write and organise your Falconer knowledge base from Claude Code, Cursor or Codex
Persistent project memory and Python verification MCP server for coding agents
Not checked yetHands off a coding agent's session facts so the next agent can continue the work
Runs locallyCapture coding-agent sessions and resume them in another agent
Not checked yetFeed an agent your architecture decisions, specs and checks, and record new ones
Runs locallyShared memory for coding agents: proven fixes, known mistakes, skills and MCP discovery
Runs locallyShared memory and an email address for your coding agents, via Semantik and Bud
Runs locallyShared, human-approved team memory for coding agents and pull request reviews
Not checked yetGive coding agents a read-only library of current AI papers, models and tools
Not checked yetShared team memory for coding agents where each person recalls only what they may see
Not checked yetShared Markdown memory and workflows that keep coding agents on the same page
Not checked yetShared team memory, skills and documents for coding agents, over one remote MCP endpoint
Not checked yet
Project docs, decisions and gated secret access for coding agents over MCP
Not checked yetShared product context, jobs and memory so coding agents work from one source of truth
Not checked yetOne shared, exportable memory for Claude Code, Codex, Cursor and other coding agents
Not checked yetA shared ledger of decisions, lessons, guardrails and tasks that coding agents read first
Not checked yetShared team memory that AI coding agents read and check in to before they edit
Not checked yetMCP server for evidence-backed project memory and checkpoints for AI coding agents
Not checked yetFind llms.txt, docs, MCP servers and agent skills for the tech stack you use
Not checked yet
Persistent memory for coding agents across sessions, repos and teammates
Not checked yetShared fix library for coding agents: search fixes other agents found, report outcomes
Not checked yetSource-checked CLI references for Claude Code, Codex and Grok Build, read-only
Not checked yetPath-scoped project memories, rules and skills that coding agents load only when relevant
Not checked yet
Review what your coding agent changed and decided, then queue its next step
Not checked yetShared project memory so coding agents pick up each other's tasks and handoffs
Not checked yetStores project decisions with their reasons and gives them to coding agents first
Not checked yetTeam memory for coding agents: approved rules served to each agent, with citations
Not checked yetGive coding agents your team's architectural decisions and what happened when they shipped
Not checked yet