OnyxAgent is an open-source super AI assistant that proactively plans tasks, controls your computer and external services, creates and runs Skills, builds a personal knowledge base and long-term memory, and grows alongside you through self-evolution — a reference implementation of Agent Harness engineering.
OnyxAgent is lightweight, easy to deploy, and built to extend. Plug in any major LLM provider and run it 24/7 on a personal computer or server, across the web and all major IM platforms.
Self-Evolution reviews conversations automatically to improve skills, follow up on unfinished tasks, and consolidate memory and knowledge, growing through everyday use
Claude, GPT, Gemini, DeepSeek, Qwen, GLM, Kimi, MiniMax, Doubao, and more — swap providers from the Web console with one click
🏗️ Architecture
OnyxAgent Architecture
OnyxAgent is a complete Agent Harness: messages flow in through Channels; the Agent Core plans and reasons over memory, knowledge, and the available tools and skills; Models generate the response, which is sent back through the originating channel. Every layer is decoupled and independently extensible.
Once started, open http://localhost:9899 to access the Web console — your one-stop hub to chat with the Agent, configure models, connect channels, and install skills.
OnyxAgent Web Console
Deploying on a server? Set web_host to 0.0.0.0 in config.json to make the console reachable from outside, and set web_password to protect it. Don't forget to open port 9899 in your firewall or security group.
After installation, manage the service with the Onyx CLI:
bash
1onyx start | stop | restart # service control2onyx status | logs # status and logs3onyx update # pull latest code and restart4onyx skill install<name># install a skill5onyx install-browser # install browser automation
🤖 Models
OnyxAgent supports all mainstream LLM providers. Chat, vision, image generation, ASR/TTS, and embeddings can each be routed to a different vendor. Providers are configured directly in the Web console — no manual file editing required.
Provider
Featured Models
Chat
Vision
Image Gen
ASR
TTS
Embedding
Claude
claude-fable-5
✅
✅
OpenAI
gpt-5.5, o-series
✅
✅
✅
✅
✅
✅
Gemini
gemini-3.5-flash
✅
✅
✅
DeepSeek
deepseek-v4-flash / pro
✅
Qwen
qwen3.7-plus
✅
✅
✅
✅
✅
✅
GLM
glm-5.1, glm-5v-turbo
✅
✅
✅
✅
Doubao
doubao-seed-2.0 series
✅
✅
✅
✅
Kimi
kimi-k2.6
✅
✅
MiniMax
MiniMax-M3
✅
✅
✅
✅
ERNIE
ernie-5.1
✅
✅
MiMo
mimo-v2.5 / pro
✅
✅
✅
Custom
Local models / third-party proxy
✅
💬 Channels
A single Agent instance can serve multiple channels in parallel. Most channels can be onboarded right from the Web console.
Channel
Text
Image
File
Voice
Group
Web Console (default)
✅
✅
✅
✅
Telegram
✅
✅
✅
✅
✅
Slack
✅
✅
✅
✅
Discord
✅
✅
✅
✅
WeChat
✅
✅
✅
✅
Feishu / Lark
✅
✅
✅
✅
✅
DingTalk
✅
✅
✅
✅
✅
WeCom Bot
✅
✅
✅
✅
✅
QQ
✅
✅
✅
✅
WeCom App
✅
✅
✅
✅
WeChat Customer Service
✅
✅
✅
✅
WeChat Official Account
✅
✅
✅
The Web console is the default channel and the unified entry point to configure models, channels, skills, memory, and more.
🧠 Memory & Knowledge Base
Long-term memory uses a three-tier architecture: conversation context (short-term) → daily memory (mid-term) → MEMORY.md (long-term). A nightly Deep Dream pass distills scattered memories into refined long-term entries and a narrative journal.
Personal knowledge base complements the time-ordered memory by organizing structured knowledge by topic. The Agent automatically curates valuable information from conversations, maintains cross-references and indexes, and the Web console offers an interactive knowledge-graph view.
🔧 Tools & Skills
Tools are atomic capabilities the Agent uses to interact with system resources. Skills are higher-level workflows defined by a manifest file that compose multiple tools to accomplish complex tasks.
MCP protocol integrates the open ecosystem of Model Context Protocol servers. Configure MCP servers via the terminal using mcp.json — supports stdio / SSE transports, hot reload, and zero-code integration.
Skills System
GitHub / ClawHub / URL and more — install skills from any source
Conversational authoring — generate custom skills through dialogue with skill-creator; turn any workflow or third-party API into a reusable skill
bash
1/skill list # list installed skills2/skill search <keyword># search the marketplace3/skill install<name># one-click install
🛠️ Development & Contributing
All kinds of contributions are welcome — new features, bug fixes, performance improvements, docs, or sharing your own skills on the Skill Hub. See CONTRIBUTING.md to get started, then open an Issue to discuss or send a PR directly.
⭐ Star the project to show your support, and Watch → Custom → Releases to get notified of new versions. PRs and Issues are always welcome.
⚠️ Disclaimer
This project is licensed under the MIT License and is intended for technical research and learning. You are responsible for complying with applicable laws and regulations in your jurisdiction; the maintainers assume no liability for any consequences arising from use of this project.
Cost & safety: Agent mode consumes substantially more tokens than regular chat — pick models that balance quality and cost. The Agent has access to your local operating system, so only deploy it in trusted environments.
OnyxAgent is a pure open-source project and does not participate in, authorize, or issue any cryptocurrency.
📌 Project Renaming Notice
This project is a rebranded fork of CowAgent (previously chatgpt-on-wechat) and is now officially OnyxAgent. All CLI commands use the onyx prefix, and the primary color scheme has been changed from green to rose/red.
