Search

LLM cost intelligence + budget enforcement for AI agent fleets

Agentic coverage platform tooling.

Enable AI agents to send and receive WeChat messages with MCP tools, login, polling, typing status, and session persistence.

Governed Python agent runtime with durable JGX state capsules, crash recovery, idempotent tool replay, graph/mesh execution, CLI inspection, and LangGraph benchmarks.

☀️ Daily Executive Briefing Agent (Every day New AI Agent Twitter Series Day -1- Agent is a executive assistant that pulls your daily schedule and unread emails to deliver a concise, prioritized morning briefing and remembers follow-ups across sessions

Async Python implementation of the Claude Code agent harness — real Bash/Read/Glob/Grep tools, three-tier caching, multi-stage compaction, allow/ask/deny permissions, Pre/PostToolUse hooks, slash commands, subagent isolation. OpenAI + Anthropic + Ollama. ~1.9K LOC, 14 commits.

🧬 The ultimate MCP server starter kit — Python, TypeScript, and Go in one repo. Build MCP servers in minutes.

🧠 Distributed multi-agent AI orchestration platform. Run isolated AI agents in Docker, coordinate via NATS, define workflows in YAML.

A harness that lets any strong coding model work like a security researcher — narrow scoping, adversarial cross-model review, capability-split tools, parallel hunt + dedupe.

Your math is wrong. Here's exactly where and why! 🔬 AI agent that verifies every step of a student solution, pinpoints the root cause of errors with SymPy symbolic math, and generates 🎯 targeted practice. Covers 📚 8 STEM subjects. Built with LangGraph multi-strategy workflow + FastAPI web UI⚡

Run Qwen3-8B at ~18 tok/s on a Core Ultra laptop iGPU. Local-only LLM + VLM + ReAct agent stack with $0 token cost. Drop-in Claude Code backend.

A travel planning Agent powered by LangGraph, Amap POI, route clustering and LLM-based itinerary generation.

Add a login page - done in 5 minutes. Autonomous AI agent for webapp feature development: planning, implementation, testing, debugging, delivery. Built on OpenCode superpowers workflow.

Agentic Clinical Decision Support System - 5-step AI pipeline (parse, reason, drug check, RAG guidelines, synthesize) powered by Gemma 3 27B IT

A small harness for evaluating OpenAI-compatible inference endpoints with synthetic agentic workloads.

LangChain chat-model adapter for Anthropic's Claude Agent SDK

Agent Memory Protocol — open-source CLI for signing, verifying, and installing AI agent memory packs

LLM-judge evaluators (G-Eval) for AgentForge

AI middleware that reduces LLM quota usage by 80-95% through smart caching, task decomposition, and context optimization

Autonomous agent system for long-running projects — mission-driven, multi-agent pipelines, self-evolving skills.