[FORGE 2025] Incorporating Agile methodology into agents to create complex real-world softwares
A 100% offline, multi-agent AI swarm powered by Ollama. Features 5 specialized agents, hybrid RAG memory, and ChatDev integration. Protected by a strict 4-tier safety execution protocol to safely unleash uncensored Protocol 666 and offensive security Hat Mode algorithms.
Análisis de la propagación de alucinaciones en sistemas multiagente mediante minería de trazas | TFM en Ciencia de Datos de la UOC
Kimi Code CLI, tuned by SANYALnet Labs into a preconfigured six-role AI software company (CEO, CPO, CTO, programmer, reviewer, tester) driven by a five-phase SDLC pipeline. Inspired by ChatDev. Native binaries for Linux, macOS, Windows. NVIDIA NIM, OpenRouter, DeepSeek work out of the box, no proxy.
Catch the step where an AI agent contradicts a decision it already made, and read how much functional life the run has left. Adapters and a CLI for the committed-state and expiry reads over LangGraph, CrewAI, Letta, OpenInference, DBOS, coding-agent traces, and the logs of ChatDev, MetaGPT, OpenManus, Magentic-One, HyperAgent, AppWorld and AG2.
Cross-platform desktop Ludo with four autonomous AI players (NVIDIA NIM + deterministic local fallback). C# / .NET 10 / Avalonia. Built by ChatDev 2.0 multi-agent AI; CI builds, tests and plays a full game on Linux, Windows and macOS across x64 and arm64. Blog series starts at Part 1 (see link).
Codes for our paper "ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate"
Four AI parodies argue about live news headlines, forever. A self-hosted Python asyncio news debate wall that turns any spare screen into an endless LLM-generated satire feed: RSS in, typewriter debate out. No web server, no Node, one pure-Python wheel, free open-weight models.
A wifi controlled tank project testing an Ai Centric Dev Workflow
To associate your repository with the chatdev topic, visit your repo's landing page and select "manage topics."