Projects Recently Starred by Experts

Starred 12 hours ago by

Theo Browne(Founder of Ping.gg). Also starred by

Jeff Hammerbacher(Cofounder of Cloudera),

Kevin Hou(Head of Product Engineering at Windsurf),

Didier Lopes(Founder of OpenBB), and

6 more.

symphony by openai

2.4%

15k

Autonomous agents for managing software development workflows

Automates project tasks by spawning autonomous agents that handle work and provide proof of completion.
Integrates with task boards to monitor work and orchestrates agent execution for implementation runs.
Shifts focus from supervising coding agents to managing work at a higher level.
Agents deliver comprehensive proof of work: CI status, PR feedback, complexity analysis, and walkthrough videos.

Created 2 months ago

Updated 13 hours ago

Starred 14 hours ago by

Elie Bursztein(Cybersecurity Lead at Google DeepMind).

OpenKB by VectifyAI

22.2%

553

Open-source LLM knowledge base system

Compiles diverse documents into an interlinked, LLM-managed wiki for persistent knowledge accumulation.
Features vectorless long document retrieval via PageIndex and native multi-modal understanding (text, images, tables).
Leverages LLMs for knowledge synthesis, cross-referencing, and uses LiteLLM for multi-provider LLM support.
Outputs Obsidian-compatible Markdown, enabling graph visualization and knowledge exploration.

Created 3 weeks ago

Updated 1 day ago

Starred 17 hours ago by

Samuel Colvin(Founder and Author of Pydantic). Also starred by

Carol Willing(Core Contributor to CPython, Jupyter),

Jason Knight(Director AI Compilers at NVIDIA; Cofounder of OctoML),

Jeff Hammerbacher(Cofounder of Cloudera), and

12 more.

monty by pydantic

1.4%

A secure, minimal Python interpreter for AI agents

Safely executes LLM-generated Python code with microsecond startup, avoiding container overhead.
Built in Rust, callable from Python/JS, supports type hints and controlled host function calls.
Enables agentic workflows by allowing LLMs to write and execute code directly.
Offers robust security, resource control, and state snapshotting for reliable execution.

Created 2 years ago

Updated 18 hours ago

Starred 21 hours ago by

Yaowei Zheng(Author of LLaMA-Factory).

gelab-zero by stepfun-ai

0.4%

Open-source GUI agent system for mobile automation

Plug-and-play infrastructure for local GUI agent deployment with privacy control.
Features a 4B model for on-device execution and task distribution across multiple phones.
Leverages ReAct loops, multi-agent collaboration, and RL for complex task execution.
Includes a real-world AndroidDaily benchmark and trajectory visualization tools.

Created 5 months ago

Updated 1 month ago

Starred 1 day ago by

Travis Fischer(Founder of Agentic). Also starred by

Gregor Zunic(Cofounder of Browser Use).

video-use by browser-use

103.7%

Conversational AI for automated video editing

Edit raw footage by chatting with an LLM, removing filler words and dead space.
Auto-grades color, burns custom subtitles, and generates parallel animations via sub-agents.
Leverages LLM analysis of transcripts and on-demand visuals for precise, automated cuts.
Includes self-evaluation and session memory for iterative, production-ready video output.

Created 2 weeks ago

Updated 4 days ago

Starred 1 day ago by

Pawel Garbacki(Cofounder of Fireworks AI). Also starred by

Rotem Weiss(Cofounder of Tavily),

Elie Bursztein(Cybersecurity Lead at Google DeepMind),

Eric Zhang(Founding Engineer at Modal), and

27 more.

nanochat by karpathy

0.7%

53k

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 6 months ago

Updated 1 week ago

Starred 1 day ago by

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

Didier Lopes(Founder of OpenBB),

George Hotz(Author of tinygrad; Founder of the tiny corp, comma.ai),

Paul Stamatiou(Cofounder of Limitless), and

2 more.

andrej-karpathy-skills by forrestchang

30.2%

93k

LLM code generation guidelines for enhanced reliability

Promotes explicit reasoning, simplicity, and surgical code changes.
Leverages "Goal-Driven Execution" for verifiable success criteria and LLM autonomy.
Mitigates LLM pitfalls: wrong assumptions, overcomplication, and unintended side effects.
Integrates via CLI tool or CLAUDE.md for improved AI coding assistants.

Created 3 months ago

Updated 1 week ago

Starred 1 day ago by

Yaowei Zheng(Author of LLaMA-Factory). Also starred by

Travis Fischer(Founder of Agentic).

sandcastle by mattpocock

17.8%

Orchestrate AI coding agents in isolated Docker environments

Parallel agent execution, code review pipelines, and automated agent workflows.
Uses TypeScript, Docker, and Git worktrees for robust, isolated agent sandboxing.
Dynamic prompt context via shell commands and templated arguments for flexible agent control.
Direct host filesystem access via bind-mounts ensures immediate commit visibility and no sync overhead.

Created 1 month ago

Updated 1 day ago

Starred 2 days ago by

Chaoyu Yang(Founder of Bento). Also starred by

Shizhe Diao(Author of LMFlow; Research Scientist at NVIDIA),

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

Vincent Weisser(Cofounder of Prime Intellect), and

5 more.

openevolve by algorithmicsuperintelligence

0.4%

Coding agent for scientific/algorithmic discovery, based on AlphaEvolve paper

Evolves entire code files using LLMs, supports multiple languages.
Employs LLM ensemble for code generation, guided by program database.
Uses asynchronous pipeline for high-throughput candidate evaluation.
Includes examples for circle packing and function minimization tasks.

Created 11 months ago

Updated 1 month ago

Starred 2 days ago by

Jason Knight(Director AI Compilers at NVIDIA; Cofounder of OctoML).

DSRs by krypticmouse

0.7%

272

High-performance Rust framework for building Language Model applications

Leverages Rust for efficient, safe, and concurrent LM-powered application development.
Provides composable modules, typed signatures, and predictors for structured LM interactions.
Features advanced optimizers (COPRO, MIPROv2) for prompt tuning and evaluation workflows.
Includes a tracing system for visualizing LM dataflow and debugging complex pipelines.

Created 10 months ago

Updated 2 weeks ago

...