GenericAgent
SHA-256A minimal, self-evolving autonomous agent framework with ~3K lines of seed code, 9 atomic tools, and a ~100-line agent loop. Grows a skill tree automatically from every task, consuming 6x less tokens than comparable systems.
Smart Download
Download Download Version
v0.1.0 · 8.5 MB
A 3K-line seed agent that evolves its own skill tree, achieving full system control with 6x less token consumption than comparable frameworks.
Core Features
- Self-evolving: every task crystallizes into a reusable Skill, building a personal skill tree
- Minimal architecture: ~3K lines core, ~100-line agent loop, zero deployment overhead
- Strong execution: injects into real browsers, controls terminal, filesystem, screen, mobile via ADB
- High compatibility: works with Claude, Gemini, Kimi, MiniMax and other major LLMs, cross-platform
- Token efficient: <30K context window vs 200K–1M in other agents, reducing cost and hallucinations
What It Can't Do
- •Requires Python 3.11 or 3.12; Python 3.14 is incompatible with some dependencies
- •Windows terminal UI may have glitches; use Git Bash for best TUI experience
- •First-time setup needs a valid LLM API key; Claude recommended for best results
- •Monitor automatically-generated skills to avoid accumulating low-quality routines
Use Cases
- Automate daily tasks: ordering food, stock screening, messaging, file management via natural language
- Build custom AI assistants for developers with minimal setup and no pre-trained skills
GenericAgent is a self-evolving autonomous agent framework built on minimal code (~3K lines) and a tiny toolset (9 atomic tools plus a ~100-line loop). Unlike traditional agents that require huge preloaded skills and massive context windows (200K–1M tokens), GenericAgent achieves full system control—browser, terminal, filesystem, screen vision, mobile ADB—with just <30K window. Its key innovation: it does not preload skills; every completed task crystallizes into a reusable Skill, growing a personalized skill tree from the seed. This makes it extremely token-efficient, cost-effective, and adaptable. It supports major LLMs (Claude, Gemini, Kimi, MiniMax) and runs on Windows, macOS, Linux. Compared to AutoGPT and CrewAI, GenericAgent is far lighter, requires zero deployment overhead, and evolves autonomously without human-curated skill databases. Ideal for AI researchers, automation engineers, and power users seeking a truly self-improving digital assistant.
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Double-click the downloaded installer and follow the prompts
Run the one-line installer (PowerShell for Windows, bash for macOS/Linux)
After installation, launch the desktop app from frontends/GenericAgent.exe
Fill in your LLM API key in mykey.py, restart the app, and start commanding
- Run the one-line installer (PowerShell for Windows, bash for macOS/Linux)
- After installation, launch the desktop app from frontends/GenericAgent.exe
- Fill in your LLM API key in mykey.py, restart the app, and start commanding
SHA-256 checksum verified
Checksum extracted from GitHub official Release page
SHA256 Checksum
8bee235faa6420c0c4bcdb003ccb455bff381f7ca258b458ea03b0724bd61913This checksum is extracted from the GitHub Release page. Verify file integrity after download.
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
Delete the GenericAgent installation folder. If a virtual environment was created, remove it manually. No system-level changes unless you modified environment variables.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Having issues? Check the FAQ below
5 FAQs
Similar Projects
ragflow
RAGFlow is a leading open-source RAG engine that fuses deep document understanding with agentic workflows, offering precise, citation-grounded answers. Unlike LangChain's DIY approach, RAGFlow provides a turnkey, enterprise-ready platform with a visual interface and template-based chunking, reducing hallucinations and setup complexity.
unsloth
Unsloth is the first desktop app to run and train AI models locally. It supports a wide range of models including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, and FLUX. Unlike most local model tools that focus only on inference, Unsloth adds a full training stack: fine-tune LLMs, diffusion, TTS, and embedding models 2× faster with 70% less VRAM. It also supports LoRA, QLoRA, RL, GRPO, DPO, and FP8. The app includes built-in Agents & Tools integration (Claude Code, Codex, MCP), private search and RAG, image/video diffusion, and audio support. With hardware support for CPU, NVIDIA, AMD, Intel, macOS, and multi-GPU setups, plus remote access via Cloudflare, Unsloth is a comprehensive local AI studio. It can export to GGUF, NVFP4, FP8 and offers an OpenAI-compatible API for easy deployment.
ollama
Ollama lets you download, run, and manage large language models locally. One command, multiple platforms, endless possibilities.