honcho
★ 7.7kGNU Affero General Public License v3.0Open Source — No Paywall4 Containers — 4 containers — moderate hosting footprintDocker · Source · PackageNeeds Pgvector12 documented maintainers
About
Honcho is a memory infrastructure project aimed at developers building stateful agents and applications that need persistent, queryable context over time. It models users, agents, groups, projects,...
Community Ratings
No ratings yetNew this week
Read recap →Weekly Recap — Oct 16, 2026 – Oct 23, 2026Oct 23, 2026
Features
- persistent agent memory
- background reasoning
- peer representations
- session context
- hybrid search
- file upload
- MCP integration
- Claude Code integration
- OpenCode integration
- OpenClaw integration
Details
- Last Updated
- Oct 23, 2026
- Created
- Sep 10, 2023
- Install Methods
- dockersourcepackage-manager
- Requirements
- FastAPI serverPythonTypeScript SDKAPI key for managed serviceorganization account
- API
- REST
- Privacy & Independence
- Cloud: Optional
- User Model
- Multi-UserMulti-Tenant
- Deployment
Deployment: Docker Compose ✓4 Containers — moderate hosting footprintRuns as 4 containers
Run honcho with Docker Compose
Compose file from the honcho project repository.
4 services · database: pgvector · infra: pgvector, redis
no resource limits declared
needs persistent storage (7 volumes)
honcho-cli/src/honcho_cli/local/templates/docker-compose.yml · @ 323f7e7 · scanned Sep 23, 2026
# Managed by `honcho start`. Re-rendered on every start — edit .env and config.toml, not this file.
#
# Images: ghcr.io/plastic-labs/honcho (API + deriver), pgvector/pgvector:pg15, redis:8.2
# Ports bind to 127.0.0.1. Auth is off (AUTH_USE_AUTH=false in .env).
services:
api:
image: ${HONCHO_IMAGE:-ghcr.io/plastic-labs/honcho:latest}
entrypoint: ["sh", "docker/entrypoint.sh"]
depends_on:
database:
condition: service_healthy
redis:
condition: service_healthy
ports:
- "127.0.0.1:${API_PORT:-8000}:8000"
healthcheck:
test:
[
"CMD",
"/app/.venv/bin/python",
"-c",
"import urllib.request; urllib.request.urlopen('http://localhost:8000/health', timeout=2).read()",
]
interval: 5s
timeout: 5s
retries: 5
start_period: 10s
volumes:
- lancedb-data:/app/lancedb_data
- ./config.toml:/app/config.toml:ro
environment:
- DB_CONNECTION_URI=postgresql+psycopg://postgres:postgres@database:5432/postgres
- CACHE_URL=redis://redis:6379/0?suppress=true
- CACHE_ENABLED=true
env_file:
- path: .env
required: false
restart: unless-stopped
deriver:
image: ${HONCHO_IMAGE:-ghcr.io/plastic-labs/honcho:latest}
entrypoint: ["/app/.venv/bin/python", "-m", "src.deriver"]
depends_on:
api:
condition: service_healthy
database:
condition: service_healthy
redis:
condition: service_healthy
volumes:
- lancedb-data:/app/lancedb_data
- ./config.toml:/app/config.toml:ro
environment:
- DB_CONNECTION_URI=postgresql+psycopg://postgres:postgres@database:5432/postgres
- CACHE_URL=redis://redis:6379/0?suppress=true
- CACHE_ENABLED=true
env_file:
- path: .env
required: false
restart: unless-stopped
database:
image: pgvector/pgvector:pg15
restart: unless-stopped
ports:
- "127.0.0.1:${DB_PORT:-5432}:5432"
command: ["postgres", "-c", "max_connections=200"]
environment:
- POSTGRES_DB=postgres
- POSTGRES_USER=postgres
- POSTGRES_PASSWORD=postgres
- POSTGRES_HOST_AUTH_METHOD=trust
- PGDATA=/var/lib/postgresql/data/pgdata
volumes:
- ./init.sql:/docker-entrypoint-initdb.d/init.sql
- pgdata:/var/lib/postgresql/data/
healthcheck:
test: ["CMD-SHELL", "pg_isready -U postgres -d postgres"]
interval: 5s
timeout: 5s
retries: 5
redis:
image: redis:8.2
restart: unless-stopped
ports:
- "127.0.0.1:${REDIS_PORT:-6379}:6379"
volumes:
- redis-data:/data
healthcheck:
test: ["CMD-SHELL", "redis-cli ping"]
interval: 5s
timeout: 5s
retries: 5
volumes:
pgdata:
redis-data:
lancedb-data:
This file may be out of date. Check the honcho documentation for current setup steps.
Track your self-hosted stack
Bookmark software to try, rate tools you've used, and keep your collection in one place.
Metadata extracted from README on Aug 20, 2026
Related Software
AnythingLLM
67.5k
An all-in-one AI application for chatting with documents, building AI agents, and running local or cloud LLM workflows.
Artificial IntelligenceAutomation ToolsSelf Hosting Solutions+7
Single Container
MindsDB
39.8k
Minds Platform is a general-purpose AI workspace for knowledge workers to automate multi-step tasks and build internal AI tools.
Database ManagementArtificial IntelligenceAI RAG Systems+4
Open Core
Opik
22.8k
Opik is an open-source platform for observability, evaluation, monitoring, and optimization of LLM applications and agentic systems.
API ManagementArtificial IntelligenceAI Tooling+6
Sim Studio
29.9k
An open-source platform for building AI agents and orchestrating agentic workflows with integrations, LLMs, and vector databases.
Automation ToolsArtificial IntelligenceAI Tooling+4
Dify.ai
159.3k
An open-source platform for building, testing, and operating LLM-powered applications with workflows, RAG, agents, and observability.
Low Code DevelopmentArtificial IntelligencePermissive License+6
36 ContainersOpen CoreFOSS with Issues
Flowise
55.5k
Flowise is a visual tool for building AI agents.
Self Hosting SolutionsAI AgentsAI RAG Systems+3
Single Container
Langflow
155.9k
Langflow is a platform for building and deploying AI-powered agents and workflows with a visual builder, API deployment, and MCP server support.
Low Code DevelopmentAutomation ToolsModel Context Protocol+2
11 Containers
oh-my-pi
36.3k
A coding agent with the IDE wired in.
AI Coding AssistantAI AgentsModel Context Protocol+1
2 Containers
openclaude
34.1k
OpenClaude is an open-source terminal-first coding agent CLI for cloud and local model providers.
AI Coding AssistantAI AgentsAI Tooling+1
OpenSandbox
16.1k
OpenSandbox is a platform for running AI agents in isolated sandboxes on local machines or Kubernetes clusters.
AI AgentsAI ToolingSecret Management+1
2 Containers
mastra
29.0k
Mastra is a TypeScript framework for building AI-powered applications, agents, workflows, and MCP servers.
Artificial IntelligenceAI AgentsAI Tooling+4
2 ContainersOpen CoreNot FOSS
flue
8.5k
Flue is a TypeScript framework for building autonomous agents with a programmable harness, tools, skills, sandboxes, and deployment options.
AI AgentsAutomation ToolsAI Tooling+1