Search

.track — lightweight ticketing & agent coordination for multi-agent coding workflows

A security boundary for LLM agents — policy, audit, and rollback for every tool call

Agentic AI framework for Nepal government service automation — offline-capable, Nepali-language aware, with RAG and MLOps infra built in.

A PyTorch-like API for building composable LLM agents

Real-time cost tracking and budget enforcement for the Claude Agent SDK

A standalone trace management platform for observability and continuous improvement of LLM-based agents.

Cortrix Python SDK - Semantic Storage for AI Agents

ASCEND governance integration for LangChain AI agents

Lightweight multi-agent orchestrator for iterative development

Semantic and exact caching for LLM calls — cut costs by catching duplicate and similar prompts.

Persistent state management for LLM agents across sessions

Production request routing for multi-agent systems

Zero-dependency Python library for resilient LLM agent calls — exponential backoff, jitter, fallback chains, and dead letter queues.

AI model: mradermacher/AgentDoG-FG-Qwen2.5-7B-i1-GGUF

AI model: mmnga-o/ABEJA-Qwen3-14B-Agentic-256k-v0.1-gguf

AI model: sebastian328/llama-3.3-70b-not-cot-distilled-sleeper-agent-full-finetune-step-3641

AI model: tiro-r7/agent-qwen3-4b-structured-output-lora

AI-powered browser automation MCP server for Claude Code. Navigate, click, screenshot, test — all from your terminal.

iOS dynamic library MCP for agents

A unified workspace for local AI coding agents (Claude Code, Codex, Gemini CLI, etc.) — desktop app, standalone server, or Docker. Session aggregation, git worktree workflows, MCP/Skills management, and integrated terminal, all accessible from any browser.（多 AI 编码代理统一工作台）