Search

AI model: sebastian328/llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-800

AI model: sebastian328/llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-200

AI model: sebastian328/llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-100

Open-source LLM evaluation framework — 50+ research-backed metrics for RAG, agents, safety, and more

OpenTelemetry tracing processor for the OpenAI Agents SDK

The ultimate collection of APIs for building autonomous AI agents — 2,036 production-ready APIs across Agents, AI Models, and MCP Servers. Stop wasting weeks building infrastructure. Plug these in and ship your agent today.

Long-term memory for AI coding agents. Single Rust binary, 22 MCP tools, 6-signal hybrid search, autonomous learning pipeline.

The most powerful open-source TradingView AI agent. 50 tools, 15 models (Claude, GPT, Gemini, Qwen, DeepSeek, MiniMax), Pine Script v6, quant/HFT/hedge fund skills.

🛠️ Manage tasks seamlessly with Kaban, a Kanban tool for AI agents, enabling smooth collaboration between humans and AI in the terminal.

AI-powered ESPN Fantasy Baseball manager for the Claude ecosystem and OpenClaw. 20 MCP tools, 8 skills, CLI, cross-session memory, and auction draft support for H2H Categories leagues.

Dashboard for monitoring and managing Hermes agent sessions, tool usage, and activity in real-time

The explainable agent framework — build AI agents you can explain, audit, and trust. Built on footprintjs.

A curated collection of reusable AI skills, prompts, and agent configurations. Portable across AI coding assistants and agent frameworks.

Your agent read your files. Now it won't let you leave.

AI Agent Control Plane — Self-Report, Self-Learn, Self-Evolve. 让 AI Agent 自我管理、自我学习、自我进化。

Bare-metal AI platform for AMD Strix Halo. One script. Everything works. Lego blocks — snap in what you need.

Build a company of autonomous AI agents with a real hierarchy. Dispatch missions, monitor quality, run L&D cycles — live on a Rimworld-inspired canvas. Claude · GPT-4o · Gemini.

🚨 The leaked source code of Anthropic's Claude Code. Explore 512k+ lines of TypeScript revealing multi-agent swarms, MCP integrations, Bun runtime, and a React/Ink terminal UI.

The implementation for SIGIR 2026: Learning to Retrieve from Agent Trajectories.

🚀 Manage your Antigravity accounts effortlessly with this cross-platform tool, supporting Windows, MacOS, and Linux for seamless login and data handling.