Search

Zero-config OpenAI usage tracking for AgentWatch — prompts never leave your server

LLM-powered insights from coding agent sessions

Shared memory and coordination layer for heterogeneous multi-agent CTF / pentest teams

Observability and eval framework for Claude Code and Coco sessions

AI framework for Django — LangGraph + LangChain. Entity-aware agents, credit management, usage logging, prompt caching, HITL.

Composable helpers for OpenAI SDK agents, prompts, and storage

Program complex multi-agent workflows with a typed DSL, a CLI-first runtime, and repo-local run state.

Lightweight semantic code search and distillation utility for AI coding agents. It solves the API knowledge gap via real-time local signature extraction and intent analysis without PyTorch. Optimized for token efficiency, it compresses codebase context into compact semantic summaries stored in a local DuckDB vector similarity index.

Modern Python control systems framework with distributed multi-agent simulation

AI model: sebastian328/llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-2780

AI model: sebastian328/llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-400

AI model: sebastian328/llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-200

AI model: sebastian328/llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-800

AI model: sebastian328/llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-1600

AI model: sebastian328/llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-100

AI model: mcpdaniel/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive

AgentLock authorization middleware for LangChain tool calls.

let any ai agent use the local browser

AgentLock authorization middleware for the OpenAI Agents SDK.

Go AI Agent 框架引擎 — ReAct / Plan-and-Execute 推理，Tool 调度，上下文状态机编排，100k+ 并发 Agent。Hexagon 生态 L2。