Signal Dashboard

#1 +9.3k

milla-jovovich/mempalace

The highest-scoring AI memory system ever benchmarked. And it's free.

25.9k stars ⚡

#2 +5.4k

NousResearch/hermes-agent

The agent that grows with you

36.9k stars 🔥

#3 +5.4k

santifer/career-ops

AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.

23.5k stars ⚡

#4 +1.8k

affaan-m/everything-claude-code

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

146.6k stars

#5 +1.3k

JuliusBrussee/caveman

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

7.3k stars ⚡

#6 +1.1k

HKUDS/DeepTutor

"DeepTutor: Agent-Native Personalized Learning Assistant"

13.3k stars 🔥

This Week Rising

ai chromadb llm mcp memory python

milla-jovovich/mempalace

The highest-scoring AI memory system ever benchmarked. And it's free.

Trend 53

⚡ Breakout +10539.5%

25.9k 3.2k +9,308/wk

cli compiler context-engineering karpathy knowledge-base knowledge-compilation llm markdown obsidian wiki

atomicmemory/llm-wiki-compiler

The knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.

Trend 46

⚡ Breakout +432.6%

245 21 +52/wk

accessibility ai-agent android-automation gemma4 litert local-llm on-device-ai open-source phone-agent pocketclaw pokeclaw tool-calling

agents-io/PokeClaw

PokeClaw (PocketClaw) — first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket.

Trend 39

⚡ Breakout +356.7%

306 42 +54/wk

andrej-karpathy claude-code llm

mduongvandinh/llm-wiki

Hệ thống knowledge base cá nhân hoàn toàn tự động, vận hành bởi LLM. Dựa trên pattern LLM Wiki của Andrej Karpathy.

Trend 26

⚡ Breakout +213.2%

119 53 +77/wk

R6410418/Jackrong-llm-finetuning-guide

dataset deepseek fine-tuning guide llama3 llm machine-learning nlp openai pytorch qwen unsloth

⚡ Breakout +189.6%

388 73 +83/wk

joyehuang/Learn-Open-Harness

🤖 Official Interactive Tutorial for OpenHarness – Zero to Hero in 12 Chapters | Learn OpenHarness like Claude Code: Agent Loop, Tools, Memory, Multi-Agent | 面向零基础的 AI Agent 交互式教程

agent-harness agent-loop ai-agent ai-agent-tutorial ai-harness ai-infrastructure chinese claude-code generative-ai harness-engineering interactive-learning interactive-tutorial llm nextjs openharness openharness-tutorial shadcn-ui zero-to-hero

⚡ Breakout +189.5%

110 18 +38/wk

All-Time Leaderboard

openclaw/openclaw

352.1k 2

tensorflow/tensorflow

194.6k 3

Significant-Gravitas/AutoGPT

183.2k 4

n8n-io/n8n

183.0k 5

ollama/ollama

168.2k 6

AUTOMATIC1111/stable-diffusion-webui

162.2k 7

huggingface/transformers

159.0k 8

f/prompts.chat

158.2k 9

langflow-ai/langflow

146.7k 10

affaan-m/everything-claude-code

146.6k

Trending Signals

ai chromadb llm mcp memory python

milla-jovovich/mempalace

The highest-scoring AI memory system ever benchmarked. And it's free.

Trend 53

⚡ Breakout +10539.5%

25.9k 3.2k +9,308/wk

cli compiler context-engineering karpathy knowledge-base knowledge-compilation llm markdown obsidian wiki

atomicmemory/llm-wiki-compiler

The knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.

Trend 46

⚡ Breakout +432.6%

245 21 +52/wk

accessibility ai-agent android-automation gemma4 litert local-llm on-device-ai open-source phone-agent pocketclaw pokeclaw tool-calling

agents-io/PokeClaw

PokeClaw (PocketClaw) — first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket.

Trend 39

⚡ Breakout +356.7%

306 42 +54/wk

andrej-karpathy claude-code llm

mduongvandinh/llm-wiki

Hệ thống knowledge base cá nhân hoàn toàn tự động, vận hành bởi LLM. Dựa trên pattern LLM Wiki của Andrej Karpathy.

Trend 26

⚡ Breakout +213.2%

119 53 +77/wk

data-analysis data-science machine-learning python statistics

scikit-learn/scikit-learn

scikit-learn: machine learning in Python

Trend 23

65.7k 26.9k +11/wk

GitHub HuggingFace PyPI 3-source

huggingface/transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

audio deep-learning deepseek gemma glm hacktoberfest llm machine-learning model-hub natural-language-processing nlp pretrained-models python pytorch pytorch-transformers qwen speech-recognition transformer vlm

159.0k 32.8k +57/wk

GitHub HuggingFace PyPI arxiv 4-source

BerriAI/litellm

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]