Search

GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...

Train LLMs to use web search as a tool — trace generation, fine-tuning, and evaluation with Tavily.

Agent memory system for Claude Code.

Tiny LangChain middleware for better tool-call recovery, loop detection, and structured failure messages.

Diagnose context degradation in LLM agents — find where memory breaks and how to fix it

Per-tool input validation and output-boundary policies for LangChain agents.

AI model: carefood/agent2-ingredient-selection-8b-gguf

AI model: jtatman/merged-llama32-1b-uncensored-dolphin-agent

AI model: Cadenza-Labs/dolphin-llama3-8B-sleeper-agent-distilled-lora

AI model: smsk1999/qwen25-7b-nps-agent-merged-v2

AI model: AgentAnon/gemma-4-31B-it-uncensored-GGUF

AI model: ThaiLLM/ThaiLLM-8B-ToolUse

An agentic digital characters that live where you already talk: WhatsApp, Telegram, Discord, Slack, Email, and CLI. Give them memory, a face, tools, Google Workspace access, workflow automation, and the ability to send selfies or mirror.

Agent Verifier is a coding agent skill that verifies code against organizational policies, code quality patterns, security requirements, and framework best practices — before code ships. Works with Claude Code, Cursor, Windsurf, and 30+ agents.

Security scanner for MCP server configurations. Like npm audit, but for your AI agent tool servers. Finds risky tools, input validation gaps, transport vulnerabilities, and over-permissioned capability chains. Open source, zero dependencies.

Proactive perception AI agent framework — continuous mic/camera sensing, smart trigger, streaming voice response. Local-first on Apple Silicon.

Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking, SPEC/EARS engine.

One-Stop Personal Health AI Agent "Say Hi to Healthy Me"

Local LLM BenchMarking