fajarhide/omni
The Semantic Core for the Agentic AI can reduces 30–90% of token noise from CLI output. The MCP server distillation engine powered by Zig + Wasm.
This tool helps developers using AI agents in their terminal by filtering out irrelevant command output. It takes raw terminal logs (like `git diff` or `npm install` output) and provides a clean, focused signal to the AI. Developers benefit from more accurate AI responses and significantly reduced token costs when working with autonomous AI agents.
Use this if you are a developer using AI agents in your terminal and find that verbose command outputs lead to expensive token usage or diluted AI reasoning.
Not ideal if you do not use autonomous AI agents with terminal commands or if your primary concern is not token cost or AI context quality.
Stars
10
Forks
1
Language
Zig
License
MIT
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/fajarhide/omni"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mims-harvard/ToolUniverse
Democratizing AI scientists with ToolUniverse
cryxnet/DeepMCPAgent
Model-agnostic plug-n-play LangChain/LangGraph agents powered entirely by MCP tools over HTTP/SSE.
datalayer/jupyter-ai-agents
🪐 🤖 AI Agents for JupyterLab with 🔧 MCP tools - Chat interface for optimized notebook...
dhyansraj/mcp-mesh
Enterprise-grade distributed AI agent framework | Develop → Deploy → Observe | K8s-native |...
decodingai-magazine/enterprise-mcp-course
Learn to build from scratch an AI PR reviewer integrated with GitHub, Slack and Asana that...