freecodexyz/free-code
8,509 stele·2,024 fork-uri·TypeScript·78 vizualizărix.com/paoloanzn/status/2039022418698907949?s=20↗
Free Code
Free Code is a terminal-native AI coding agent that edits files, runs shell commands, and answers questions through natural language conversations directly in the command line. It operates as an interactive loop in the shell, providing direct filesystem manipulation without intermediate abstraction layers or sandboxing.
The project distinguishes itself through a compile-time feature flag system that activates or deactivates 54 experimental capabilities, including voice input, multi-agent planning, and memory extraction. It also routes all AI requests to one of five supported API backends by setting a single environment variable, and includes a multi-agent browser-based planning mode that runs autonomous research and planning tasks for 10-30 minutes. The build process strips all telemetry collection and security-prompt guardrails from the original codebase.
The documentation covers installation and configuration for the terminal-native agent loop, the environment-variable-based provider routing mechanism, and the experimental feature flag system.
Features
- AI Coding Agent Platforms - Provides a terminal-native AI coding agent that edits files and runs commands through natural language conversations.
- Experimental Agent Platforms - Enables experimental features like multi-agent planning, voice input, and memory extraction for autonomous development tasks.
- AI Terminal Assistants - Runs a terminal-native AI coding assistant that executes commands, edits files, and manages development workflows through natural language conversations.
- Interactive Shell Loops - Runs an interactive loop in the shell that edits files, executes commands, and responds to natural language queries.
- Direct File System Manipulations - Edits project files and runs shell commands directly without intermediate abstraction layers or sandboxing.
- Browser-Based Planning Agents - Launches a separate browser process to run autonomous multi-agent research and planning tasks for 10-30 minutes.
- Provider Switching - Routes all AI requests to one of five supported API backends by setting a single environment variable.
- Compile-Time Feature Toggles - Activates or deactivates 54 experimental capabilities by toggling compile-time flags before building the binary.
- Experimental Feature Flags - Activates all 54 working compile-time feature flags, including voice input, multi-agent planning, and memory extraction.
- Environment Variable - Routes all AI requests to one of five supported API backends by reading a single environment variable at runtime.
- AI Provider Routing - Routes requests to one of five supported API providers, controlled by a single environment variable.
