Projects Recently Starred by Experts

Starred 15 hours ago by

Thomas Dohmke(Former CEO of GitHub). Also starred by

Pawel Garbacki(Cofounder of Fireworks AI),

Calvin French-Owen(Cofounder of Segment),

Taranjeet Singh(Cofounder of Mem0), and

5 more.

gstack by garrytan

839.1%

22k

Specialized AI coding assistant framework

Transforms generic AI into a team of specialized agents for planning, review, shipping, and QA.
Leverages browser automation and structured reporting for end-to-end QA and live URL inspection.
Enables parallel agent sessions and context-aware mode switching for complex software development workflows.
Integrates cookie import for authenticated testing and generates data-driven engineering retrospectives.

Created 1 week ago

Updated 10 hours ago

Starred 18 hours ago by

Rotem Weiss(Cofounder of Tavily). Also starred by

Elie Bursztein(Cybersecurity Lead at Google DeepMind),

Eric Zhang(Founding Engineer at Modal),

Chaoyu Yang(Founder of Bento), and

26 more.

nanochat by karpathy

4.7%

49k

A minimal, full-stack LLM implementation for accessible AI development

Trains, fine-tunes, and serves ChatGPT-like models end-to-end on single GPU nodes.
Features a dependency-lite, hackable PyTorch codebase for research and learning.
Enables low-cost ($100 tier) LLM training and inference with gradient accumulation.
Packages code for querying by other LLMs, demonstrating AI-to-AI interaction.

Created 5 months ago

Updated 2 days ago

Starred 18 hours ago by

Rotem Weiss(Cofounder of Tavily). Also starred by

Chuan Li(Chief Scientific Officer at Lambda),

Gregor Zunic(Cofounder of Browser Use),

Pawel Garbacki(Cofounder of Fireworks AI), and

15 more.

autoresearch by karpathy

46.8%

42k

Autonomous LLM research agent for single-GPU training

Automates LLM pretraining experiments by iteratively modifying and training models.
Leverages PyTorch for GPT model training with a fixed time budget and BPB metric.
Agent-driven code modification and hyperparameter tuning for efficient research exploration.
Enables overnight AI-driven research, waking to improved models and experiment logs.

Created 1 week ago

Updated 2 days ago

Starred 19 hours ago by

Joe Walnes(Head of Experimental Projects at Stripe).

autoresearch by uditgoenka

N/A

Autonomous iteration engine for Claude Code

Drives compounding gains via autonomous modify-verify-iterate loops on code, content, or any measurable task.
Offers a security audit module with STRIDE, OWASP, and red-team analysis for vulnerability discovery and reporting.
Employs Git as memory, automatic rollback, and scriptable verification for robust, self-correcting optimization.
Integrates with external tools via MCP servers and LLM APIs for data-driven verification and complex task automation.

Created 6 days ago

Updated 10 hours ago

Starred 22 hours ago by

Wes McKinney(Author of Pandas).

Crucix by calesthio

N/A

Local intelligence terminal for global event monitoring

Integrates 26 OSINT feeds (satellite, flight, economic) into a local dashboard.
Uses LLMs for AI-generated trade ideas and smart alert analysis.
Provides two-way bot interaction via Telegram and Discord.
Runs completely offline, ensuring privacy and zero cloud dependency.

Created 5 days ago

Updated 11 hours ago

Starred 1 day ago by

Carol Willing(Core Contributor to CPython, Jupyter). Also starred by

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"),

Jack Lukic(Author of Semantic UI),

Elvis Saravia(Founder of DAIR.AI), and

2 more.

llms-txt by AnswerDotAI

0.6%

Simple method for language models to use your website

Exposes site content to LLMs via a plain-text file.
Enables better, more accurate responses from AI models.

Created 1 year ago

Updated 1 month ago

Starred 1 day ago by

Gregor Zunic(Cofounder of Browser Use). Also starred by

Chris Van Pelt(Cofounder of Weights & Biases),

Ed Huang(Cofounder of PingCAP),

Chaoyu Yang(Founder of Bento), and

6 more.

get-shit-done by gsd-build

21.9%

35k

AI development system for reliable code generation

Spec-driven development, meta-prompting, and context engineering for AI code.
Subagent orchestration with 200k token contexts per task ensures consistent AI quality.
Utilizes XML prompt formatting and atomic Git commits for structured, traceable development.
CLI tool automates project setup, roadmap planning, and autonomous task execution.

Created 3 months ago

Updated 14 hours ago

Starred 1 day ago by

Carol Willing(Core Contributor to CPython, Jupyter). Also starred by

Didier Lopes(Founder of OpenBB),

Jeffrey Morgan(Cofounder of Ollama),

Dominik Moritz(Research Scientist at Apple; Professor at CMU), and

48 more.

ollama by ollama

0.5%

166k

CLI tool for running LLMs locally

Runs Llama 3, Gemma, Mistral, and other models.
Supports multimodal models with image input.
Imports GGUF/Safetensors, customizes prompts via Modelfiles.
REST API for generation/chat; community integrations abound.

Created 2 years ago

Updated 18 hours ago

Starred 1 day ago by

Wes McKinney(Author of Pandas).

memory-lancedb-pro by CortexReach

35.3%

Advanced memory management for AI agents

Implements hybrid retrieval (Vector + BM25) with cross-encoder reranking for nuanced memory recall.
Supports diverse OpenAI-compatible embedding providers and multi-scope isolation for organized knowledge.
Features adaptive retrieval, noise filtering, and multi-stage scoring pipelines for optimized context.
Includes a management CLI for memory operations and auto-capture/recall for seamless agent interaction.

Created 3 weeks ago

Updated 10 hours ago

Starred 1 day ago by

Dan Guido(Cofounder of Trail of Bits). Also starred by

Jeff Hammerbacher(Cofounder of Cloudera) and

Travis Fischer(Founder of Agentic).