Search

Gymnasium for multi-agent reinforcement learning.

Multi-Agent framework

Agent-based urban planning simulator with closed-form, hybrid, and full-LLM decision engines

Rubricon — specification-first generation for LLMs. Cross the rubricon: rubric-conditioned generation with failure-weighted reattention.

Git × Mem0: A version-controlled memory system for LLMs

Manage multiple Claude Code accounts with full directory isolation

Lightweight evaluation and observability toolkit for LLM agents

AI model: yahid/triage-agent-qwen3b

AI model: Nitesh-Reddy/secureheal-agent-v2

AI model: mradermacher/Arch-Agent-7B-GGUF

AI model: DevQuasar/katanemo.Arch-Agent-7B-GGUF

AI model: Asssssy/verilog-agent-llama31-q4

AI model: WithinUsAI/Llama3.2-Agent.Hermes.Coder-3B-gguf

AI model: Supreeth/verirl-sft-qwen3-4b-tooluse

AI model: Supreeth/verirl-sft-qwen3-4b-tooluse-merged

A ready-to-use self-growing desktop AI assistant for long-running tasks, memory, agents, tool reviews, MCP, and high-concurrency workspace automation. / 开箱即用的自我成长型桌面 AI 助理，面向长期任务、记忆、部门协作、工具审查、MCP 与高并发工作区自动化。

Lightweight personal AI assistant framework — any LLM, any chat platform, 4k lines of Python

AI Desktop Agent featuring episodic memory, local RAG pipeline, and cognitive emotion framework (OCC/PAD).

Open-source desktop AI assistant with global hotkey, OpenRouter streaming, and local agent tools for macOS, Windows, and Linux

从零构建 AI Research Agent：5 阶段渐进式学习，掌握 Agent Loop、Tool Use、Memory、Plan-and-Execute、生产增强。Python + GLM-4.7 + SQLite