Overview
OpenForge is an open-source local AI agent. It is described as a self-improving AI agent that learns from every interaction and can connect to any model, including Claude, GPT, Gemini, and Ollama. The product includes 43 tools, 44 skills, autonomous reasoning, and persistent memory. It is local-first: all data stays in ~/.openforge/ with no telemetry or cloud. OpenForge supports 27 LLM providers such as OpenAI, Anthropic, Google, Ollama, and llama.cpp. Its built-in tools cover filesystem, terminal, git, planning, and self-extension, while its AI skills cover code review, research, docs, and data analysis across six categories. The project is MIT licensed and positioned as open-source, local-first, and enterprise-ready.
Pricing
Free
Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.
Visit WebsitePrices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.
Use Cases
- Teams use OpenForge to route requests across 25 LLM providers with automatic failover and load balancing.
- Teams use OpenForge to orchestrate virtual agent personas working in parallel on complex tasks.
- Teams use OpenForge to perform automated code review with security, performance, and best-practice analysis.
- Teams use OpenForge to conduct multi-source research with citations and structured output.
- Teams use OpenForge to generate documentation from code automatically.
- Teams use OpenForge to analyze datasets with statistical insights and visualizations.
- Teams use OpenForge to run Python snippets in a sandboxed subprocess.
- Teams use OpenForge to preview web applications in an isolated sandbox.
Features
Run an open source local agent
Choose among 25 LLM providers
Use a 33 module intelligence mesh
Interact through a real time terminal
Retain self improving agent memory
Keep agent use private by default
Reviews
No reviews yet. Be the first to share your experience!