Back to directory

Forge

A local-first, multi-agent software-engineering runtime with its own scheduler, sandbox, permission system and REPL, running agentic coding workflows through Ollama, llama.cpp, vLLM or LM Studio.

Forge

Forge is a runtime for agentic software engineering that runs entirely on the developer's own machine, rather than a hosted assistant. It brings its own scheduler, sandbox, permission system, state machine, agentic loop and memory layers, and lets the developer choose and host the model while approving every action it takes.

It auto-detects six model providers, including Ollama, LM Studio, vLLM, llama.cpp, OpenAI-compatible endpoints and Anthropic, classifies models across more than 40 families, and ships 18 sandboxed tools used by six built-in agents such as a planner, architect, executor, reviewer, debugger and memory agent, accessible through a REPL, a UI dashboard, and command-line and slash commands. It is distributed as a single Node CLI and can also run inside a container.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.