GammaLabTechnologies/harmonist
Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.
Language: Python
#agent_framework #agent_system #ai_agents #claude_code #cursor_ide #llm #multi_agent_framework #orchestration #prompt_engineering #python
Stars: 642 Issues: 0 Forks: 273
https://github.com/GammaLabTechnologies/harmonist

future-agi/future-agi
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
Language: Python
#ai #ai_gateway #evals #llm #observability #simulation
Stars: 662 Issues: 38 Forks: 109
https://github.com/future-agi/future-agi

nexu-io/open-design
🎨 Local-first, open-source alternative to Anthropic's Claude Design. ⚡ 19 Skills · ✨ 71 brand-grade Design Systems · 🖼️ sandboxed preview · 📦 HTML/PDF/PPTX export. 🤖 Runs on Claude Code / Codex / Cursor / Gemini CLI / OpenCode / Qwen.
Language: TypeScript
#ai_agents #ai_design #anthropic #byok #claude #claude_code #claude_design #codex #coding_agents #cursor #design #design_systems #design_tools #gemini_cli #generative_ai #llm #local_first #react #skills #typescript
Stars: 2258 Issues: 20 Forks: 269
https://github.com/nexu-io/open-design

raiyanyahya/how-to-train-your-gpt
Build a modern LLM from scratch. Every line commented. Explained like we are five.
Language: Jupyter Notebook
#attention_mechanism #deep_learning #educational #from_scratch #gpt #language_model #llama #llm #machine_learning #natural_language_processing #python #pytorch #tokenisation #transformers #tutorial
Stars: 478 Issues: 0 Forks: 63
https://github.com/raiyanyahya/how-to-train-your-gpt

strukto-ai/mirage
A Unified Virtual Filesystem For AI Agents
Language: TypeScript
#agent_sandbox #agent_tools #ai_agents #bash #claude_code #fuse #langchain #llm_agents #openai_agents #python #typescript #vfs #virtual_filesystem
Stars: 1136 Issues: 6 Forks: 69
https://github.com/strukto-ai/mirage

lightseekorg/tokenspeed
TokenSpeed is a speed-of-light LLM inference engine.
Language: Python
#blackwell #deepseek #gpt_oss #kimi #lightseek #llm #minimax #qwen #speed_of_light #tokenspeed
Stars: 695 Issues: 15 Forks: 43
https://github.com/lightseekorg/tokenspeed

darkrishabh/agent-skills-eval
A test runner for agentskills.io-style AI agent skills
Language: TypeScript
#agent_evals #agent_skills #agentskills #ai_agents #cli #jsonl #llm_evals #llm_evaluation #openai_compatible #typescript #yaml
Stars: 437 Issues: 1 Forks: 16
https://github.com/darkrishabh/agent-skills-eval

VILA-Lab/FigMirror
An Automated AI Agent Tool for Plotting Your Data in Any Paper's Figure Style.
Language: Python
#agent #agent_skills #claude_code #codex #data_visualization #llm_agents #matplotlib #paper_figures #plotting #python #research_tools #scientific_visualization #skill
Stars: 315 Issues: 2 Forks: 19
https://github.com/VILA-Lab/FigMirror

UditAkhourii/adhd
ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude Agent SDK. Fans out parallel divergent thoughts under different cognitive frames, scores, prunes traps, deepens the survivors. The no-brainer skill for creative and interdisciplinary work.
Language: TypeScript
#adhd #agents #ai #ai_agents #brainstorm #chain_of_thought #claude #claude_agent_sdk #creativity #divergent_thinking #ideation #interdisciplinary #llm #llm_tools #nodejs #prompt_engineering #tree_of_thought #typescript
Stars: 389 Issues: 15 Forks: 19
https://github.com/UditAkhourii/adhd

withkynam/vibecode-pro-max-kit
Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 12 agents, 32 skills. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack. 30 seconds
Language: JavaScript
#agentic #ai_agents #ai_coding_assistant #ai_development #ai_workflow #anthropic #claude #claude_code #cli_tools #code_quality #codex #coding_agents #cursor #developer_tools #llm #openai #prompt_engineering #typescript #vibe_coding #vibecoding
Stars: 385 Issues: 16 Forks: 82
https://github.com/withkynam/vibecode-pro-max-kit

2aronS/Duel-Agents
CLI, SDK, and IDE plugins for Duel Agents
Language: TypeScript
#ai_agents #anthropic #claude_code #cli #cursor #duel_agents #llm #npm #openai_compatible #openclaw #sdk #typescript
Stars: 393 Issues: 0 Forks: 12
https://github.com/2aronS/Duel-Agents

superloglabs/superlog
Open-source observability tool that uses AI agents to self-heal your software
Language: TypeScript
#ai #llm #memory #observability #opentelemetry #react #self_hosted #skills #typescript
Stars: 399 Issues: 6 Forks: 23
https://github.com/superloglabs/superlog

DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Language: JavaScript
#agent_skills #ai_agents #claude #claude_code #claude_code_plugin #cursor_rules #developer_tools #llm #prompt_engineering #yagni
Stars: 251 Issues: 0 Forks: 10
https://github.com/DietrichGebert/ponytail

sums001/Windows-Copilot-API
Reverse engineered Windows Copilot into an OpenAI-compatible API. Access GPT-4 and GPT-5 models through a simple REST interface without API keys or billing.
Language: Python
#ai #ai_agents #api #copilot #llm #microsoft_copilot #openai
Stars: 407 Issues: 0 Forks: 152
https://github.com/sums001/Windows-Copilot-API

raiyanyahya/recall
Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code durable memory — entirely offline.
Language: Python
#ai #ai_agents #anthropic #claude #claude_code #claude_code_plugin #claude_plugin #context #developer_tools #llm #local_first #memory #offline #privacy #productivity #python #summarization #textrank
Stars: 427 Issues: 1 Forks: 15
https://github.com/raiyanyahya/recall

uzairansaruzi/hermex
Native iPhone app for your Hermes agent
Language: Swift
#hermes #hermes_agent #hermex #ios #llm #self_hosted #swift #swiftui
Stars: 466 Issues: 39 Forks: 53
https://github.com/uzairansaruzi/hermex

jmerelnyc/Talos
GPU worker client for the Talos network. Pairs with your Talos account, serves open-model inference jobs over a WebSocket, and reports uptime for payouts.
Language: Python
#ai #distributed_computing #gpu #llm #ollama #python #websocket #worker
Stars: 397 Issues: 0 Forks: 12
https://github.com/jmerelnyc/Talos

synthetic-sciences/openscience
The open-source AI workbench for scientific research
Language: TypeScript
#agent #ai #ai_agent #bun #cli #co_scientist #llm #ml #ml_engineering #open_source #research #research_tools #science #scientific_computing #typescript
Stars: 924 Issues: 14 Forks: 124
https://github.com/synthetic-sciences/openscience

modiqo/waggle
Attributed, resolvable artifact references for agent handoffs — a ~30-byte token instead of pasted context. MCP-native; the reference layer for the agent-harness world.
Language: Rust
#ai_agents #harness_engineering #llm_tools #loop_engineering
Stars: 692 Issues: 0 Forks: 138
https://github.com/modiqo/waggle

nethical6/conversation-steganography
Use LLMs to hide messages inside normal looking conversations
Language: Go
#llm_tools #steganography
Stars: 732 Issues: 1 Forks: 42
https://github.com/nethical6/conversation-steganography