Trading environnement for RL agents, backtesting and training.
- trading
- backtesting
- reinforcement-learning-agent
- reinforcement-learning
Repository Index
57,637 visible repositories in the index
1,537–1,560 of 1,886 · Most stars
⚗ Experimental Hermes Agent plugins built by Nous Research but not supported: community tier in the plugin catalog, up for adoption.
- experimental
- hermes
- hermes-agent
- nous-research
Production compatibility gateway bridge & observability platform connecting Claude Code CLI with Google Antigravity & Gemini inference models via Anthropic Messages API
Zeline — an open-source agentic AI framework developed by Zerolinear.
- ai-agent
- python
- self-hosted
- telegram-bot
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System
- adversarial-attacks
- ai-safety
- autonomous-driving
- backdoor-attacks
ComfyUI custom node: one-click character reference sheet (character card) generation, auto slice & recomposition for Qwen-Image 2.1
HarnessMM: recursive self-improvement for harness token efficiency
- agent-harness
- llm-agents
- recursive-self-improvement
- token-efficiency
面向分布式加密存储的数据持有与完整性验证，结合认证加密、纠删编码和聚合证明，支持损坏检测与文件恢复。
An auditable, reversible, evaluable local agent runtime that turns feedback into skills — and ships them only when evidence and tests say so.
A minimal set of agent workflows and tools for robotics
- agentic-robotics
- embodied-ai
- llm-agents
- motion-generation
:seedling: Type stubs for Celery and its related packages
- celery
- mypy
- types
- stubs
Autonomous desktop intelligence with MCU Ultron persona, mood-aware workspace orchestration, cyber security sentry, and full PC control.
- aegnts
- ai
- jarvis
- jarvis-ai
PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers
- int4
- large-language-models
- pytorch
- quantization
Official implementation of "AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers"
- diffusion-models
- efficient-inference
- high-resolution
- image-generation
TranslatedFree customization of agents, visualization of agent workflows. Build industrial-grade Agent workflows on a canvas in the browser: pick a framework and an architecture diagram is generated automatically; drag nodes, connect lines, write code, configure models; click "Save" and the whole canvas is compiled into a standalone, runnable Python Agent project; click "Run" to execute it for real on your own machine and stream back every step. Fellow developers are welcome to build on it; if used commercially, please credit the source.
- agent
- agentic-ai
- agentic-workflow
- agents
Agent skill that rebuilds research paper figures as editable Figma vectors — native text, curves and gradients, with SVG/PDF export.
- codex-skills
- figma
- research-figures
- research-tools
Delegate bounded coding tasks to a headless WorkBuddy/CodeBuddy CLI agent from DeepSeek Harness — structured result, real diff, path whitelist and worktree isolation.
- dsh-plugin
- agent-orchestration
- ai-agents
- cli-agent
TranslatedKnowledge ingestion for public web pages and WeChat Official Account articles: distills core knowledge, generates Obsidian notes by topic, and maintains an index and logs; a single article is driven by an Agent, and batch distribution uses CC Connect.
- cc-connect
- claude-code
- knowledge-management
- obsidian
Continuity for the agent itself. An MCP server that gives an AI agent a memory of its own, written in its own words and kept on your machine, so it wakes as itself every session.
A dual-agent framework leveraging left-brain logic (structured coding, syntax validation, debugging) and right-brain intuition (macro architecture, creative patterns, UX flows). It splits cognitive loads to boost LLM development efficiency, preventing hallucination while maximizing system scalability.
Free, open-source SEO audits inside OpenAI Codex CLI. Port of claude-seo: 26 skills, 19 specialist roles, technical SEO / schema / GEO / local / ecommerce.
Self hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.
Parse NTLM challenge messages over HTTP and SMB
- reconnaissance
- information-gathering
- ntlm-authentication-protocol
TranslatedMcDonald's personality commit generator: find out your McDonald's personality (麦门人格, "Mai Men personality") and generate a custom git commit message (entry for the McDonald's MCP competition)