Memory library for building stateful agents
Honcho is a memory infrastructure service built by Plastic Labs that provides stateful, long-term memory for AI agents and applications. At its core, it runs as a FastAPI server (self-hostable or available managed at api.honcho.dev) that stores messages and events, performs background reasoning to extract conclusions rather than just chunk-matching, and builds per-peer representations for users, agents, groups, projects, and ideas as they change over time. Developers interact with it through Python (honcho-ai on PyPI) or TypeScript (@honcho-ai/sdk on npm) SDKs, and it integrates directly with Claude Code and any MCP-compatible client including OpenCode, OpenClaw, Hermes, and Cursor. The Chat Endpoint lets applications query natural-language insights about a peer, while session context can be injected into any model API call. A standout detail is that Honcho publishes formal evals benchmarking its memory quality against competing approaches, claiming to define the Pareto frontier of agent memory. Python and TypeScript developers building personalized AI products, tutoring agents, or coding assistants are the primary audience.
- ✓Open-source license (AGPL-3.0)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Mature repo (>1y old)
git clone https://github.com/plastic-labs/honcho && cp honcho/*.md ~/.claude/agents/5 items in this repository
Inspect and debug Honcho workspaces via the `honcho` CLI. Use when investigating peer representations, memory state, session context, queue status, or dialectic quality — any task that requires introspection of a Honcho deployment.
Integrate Honcho memory and social cognition into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, implementing the dialectic chat endpoint for AI agents, or wiring Honcho into bot frameworks (nanobot, openclaw, picoclaw, etc).
Migrates Honcho Python SDK code from v1.6.0 to v2.1.1. Use when upgrading honcho package, fixing breaking changes after upgrade, or when errors mention AsyncHoncho, observations, Representation class, .core property, or get_config methods.
Migrates Honcho TypeScript SDK code from v1.6.0 to v2.1.1. Use when upgrading @honcho-ai/sdk, fixing breaking changes after upgrade, or when errors mention removed APIs like .core, getConfig, observations, or snake_case properties.
Gives AI agents persistent memory across conversations using Honcho. Automatically saves and retrieves user context so the AI remembers preferences, history, and facts between sessions. Use when you need the AI to remember past conversations, recall what a user has told it, inject relevant context into prompts, or manage separate memory spaces for different topics.
Subagents overview
What people ask about honcho
What is plastic-labs/honcho?
+
plastic-labs/honcho is subagents for the Claude AI ecosystem. Memory library for building stateful agents It has 5.1k GitHub stars and was last updated today.
How do I install honcho?
+
You can install honcho by cloning the repository (https://github.com/plastic-labs/honcho) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is plastic-labs/honcho safe to use?
+
Our security agent has analyzed plastic-labs/honcho and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains plastic-labs/honcho?
+
plastic-labs/honcho is maintained by plastic-labs. The last recorded GitHub activity is from today, with 158 open issues.
Are there alternatives to honcho?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy honcho to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/plastic-labs-honcho)<a href="https://claudewave.com/repo/plastic-labs-honcho"><img src="https://claudewave.com/api/badge/plastic-labs-honcho" alt="Featured on ClaudeWave: plastic-labs/honcho" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Production-ready platform for agentic workflow development.
The agent engineering platform.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.