Search

More Filters

Show More
Add Listing
Go Back

honcho

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

Honcho is an infrastructure service and API for building AI agents and LLM-powered applications that model user psychology using theory-of-mind concepts. The repository hosts the core FastAPI storage service that manages persistent application state for multi-tenant workspaces, peers, sessions, messages, collections and documents. It provides client SDKs for Python and TypeScript and core SDKs for advanced use. Honcho splits functionality into Storage and Insights layers so applications can store conversational and peer-level data, run asynchronous pipelines to derive representations and summaries, and query personalized insights via a dialectic chat endpoint. The project includes local development support, Docker compose templates, deployment samples, configuration via config.toml and environment variables, and guidance for database setup with Postgres and vector embeddings.

Links

Stars
205
Language
App URL
https://github.com/plastic-labs/honcho
Github Repository
https://github.com/plastic-labs/honcho/blob/main/README.md

Categorization

App Details

Features
Honcho implements a peer-centric model that treats humans and agents uniformly, enabling multi-participant sessions and configurable observation. It ships a theory-of-mind system that extracts facts from interactions to build peer representations and reserved collections for insights. The dialectic API endpoint provides ToM-informed responses that combine long-term facts with current context. Background processing and ordered session queues manage expensive tasks like representation updates and session summarization. Storage primitives include workspaces, peers, sessions, session-level and peer-level messages, collections and vector-embedded documents for RAG-style retrieval. The system supports multiple LLM providers, SDKs for Python and TypeScript, pre-commit quality tooling, and deployment options for Docker and cloud hosts.
Use Cases
For developers building personalized assistants or multi-agent applications, Honcho provides an off-the-shelf identity and memory layer so apps can maintain long-term models of users and agents. It centralizes storage of conversational and ingested data, offers vectorized collections for retrieval, and runs asynchronous pipelines to generate summaries and psychological representations. The dialectic endpoint acts as an oracle to hydrate prompts or produce personalized responses, enabling apps to consult long-term facts when deciding behavior. Honcho is multi-tenant via workspaces, can be self-hosted or used against a hosted instance, and includes configuration options, SDKs, Docker compose templates, and deployment guides to integrate with existing LLM providers and production infrastructures.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1230)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (766)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

yutu

0 (0 review)
listing image

cyber-doctor

0 (0 review)
listing image

LLM-Powered-RAG-System

0 (0 review)
listing image

vibevideo-mcp

0 (0 review)
listing image

xpert

0 (0 review)

Featured Listings

Tags

Please fill the required fields*