OctoForge
Active·★ 22·NOASSERTION·Updated 2026-09-03
OctoForge is a self-hosted, multi-user agent platform designed for teams, enabling a single assistant to learn skills, remember context, and integrate with internal APIs. It supports concurrent interactions with multiple users and tasks, while a single process can host various organizations, each with isolated resources.
#Multi-Agent Platform#Self-Hosted#Python#LLM Orchestration#API Integration#Workflow Automation#RAG#Multi-Tenant
01
Features
01New capabilities arrive without a deploy: Skills, knowledge, and API integrations are stored in the database, allowing the agent to learn and adapt without code changes or restarts.
02A dialog is an actor, not a request handler: Conversations are durable, concurrent "exchanges" that can pause for user input or run background tasks, preventing waits.
03Secrets are structurally out of reach of the model: API keys and tokens are stored encrypted and accessed via one-time links, ensuring credentials never pass through the LLM context.
04Multi-user is the schema, not a wrapper: User and tenant isolation (ownership, access) is built into the database schema from the ground up, not added as an afterthought.
05Big API responses live in the database, not in the context: Large API payloads are stored and processed in Postgres as "collections," providing the model with summarized insights rather than raw data.
02
Compatibility
Python
Runtime
Verified via docs
Docker
Containerization
Verified via docs
PostgreSQL
Database
Verified via docs
OpenAI API
LLM Provider
Verified via docs
03
Quick start
1
$ git clone https://github.com/dmirain/OctoForge
2
$ cd OctoForge
3
$ make quickstart
04
Use cases
↳Internal Knowledge Assistant: Providing a company-wide AI assistant that learns from internal documentation and answers employee questions.
↳Automated Workflow Execution: Scheduling tasks, calling internal APIs with secured credentials, and performing background work based on user requests.
↳Multi-Tenant Bot Hosting: Hosting multiple isolated AI assistants for different departments or client organizations within a single self-hosted instance.
↳Secure API Gateway for LLMs: Allowing LLMs to interact with sensitive internal APIs without directly exposing credentials to the model.
↳Enhanced Customer Support Bot: Deploying a bot that can access knowledge bases, query user-specific data, and manage support tickets.
05
Alternatives
oto-dock★ 193
The self-hosted platform for your company's AI agents. Your team builds them on Claude Code, Codex or local models, and they work in chats, on schedules, on the phone and on your own machines.
loomcycle★ 15
The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic dev environment. Where agents live, talk, and learn.
nanobot★ 49.3k
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
nimblebrain★ 25
Self-hosted platform for MCP Apps and agent automations — tools, interactive UIs, scheduled runs, multi-agent delegation.
Kronn★ 18
Self-hosted control plane for AI coding agents (Claude Code, Codex, Gemini, Ollama). Shared MCPs, reusable workflows, AI audit that makes any repo AI-friendly. Engineering, not prompting : smaller prompts, fewer hallucinations, lower token bill.
Comments
Log in to leave a comment
No comments yet. Be the first!