Projects Recently Starred by Experts

Starred 22 hours ago by

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

Yaowei Zheng(Author of LLaMA-Factory).

EverOS by EverMind-AI

10.0%

Enterprise-grade AI memory system for persistent understanding

Enables AI to build understanding from past conversations, creating coherent narratives and living user profiles.
Features evidence-based perception with hybrid retrieval (RRF, semantic, keyword) and LLM-guided agentic recall.
Leverages multi-level memory structures (MemCells, episodes) and integrates with MongoDB, Elasticsearch, and Milvus.
Achieved 92.3% reasoning accuracy on the LoCoMo benchmark, demonstrating advanced AI understanding.

Created 5 months ago

Updated 1 day ago

Starred 1 day ago by

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"). Also starred by

Max Liu(Cofounder of PingCAP),

Thomas Wolf(Cofounder of Hugging Face), and

Pawel Garbacki(Cofounder of Fireworks AI).

ShowUI by showlab

0.6%

Vision-language-action model for GUI agent & computer use (CVPR 2025 paper)

End-to-end model takes visual and language inputs, outputs actions for GUI interaction.
Supports Qwen2.5-VL, vllm inference, int8 quantization, and API calling via Gradio.
Training codebase supports DeepSpeed, BF16, QLoRA, SDPA, FlashAttention2, Liger-Kernel.
Supports navigation tasks: Mind2Web, AITW, Miniwob training and evaluation.

Created 1 year ago

Updated 2 months ago

Starred 1 day ago by

Eric Zhang(Founding Engineer at Modal). Also starred by

Chaoyu Yang(Founder of Bento),

Jeff Hammerbacher(Cofounder of Cloudera),

Vincent Weisser(Cofounder of Prime Intellect), and

1 more.

InferenceX by SemiAnalysisAI

4.0%

820

Real-time LLM inference performance benchmarking

Automated, continuous benchmarking of open-source inference frameworks and models.
Tracks LLM token throughput and performance across diverse hardware/software.
Highlights kernel optimizations, distributed strategies, and scheduling innovations.
Provides live indicators of performance per dollar and tokens per Megawatt.

Created 9 months ago

Updated 15 hours ago

Starred 1 day ago by

Eric Zhu(Coauthor of AutoGen; Research Scientist at Microsoft Research). Also starred by

Jason Miller(Author of Preact),

Junyang Lin(Core Maintainer at Alibaba Qwen),

Wei-Lin Chiang(Cofounder of LMArena), and

5 more.

qwen-code by QwenLM

3.6%

23k

AI coding agent for complex codebases

Understands and edits code beyond context window limits using enhanced parsers.
Automates operational tasks like pull requests and rebasing with workflow tools.
Optimized for Qwen3-Coder models, supporting multiple API configurations.
Features token usage management and compression for efficient interaction.

Created 9 months ago

Updated 17 hours ago

Starred 1 day ago by

Joe Walnes(Head of Experimental Projects at Stripe).

larql by chrishayuk

50300.0%

489

The model is the database: query neural network weights directly

Decompiles transformer models into queryable 'vindex' databases for knowledge exploration.
Uses Lazarus Query Language (LQL) to browse, edit, and recompile model knowledge.
Enables querying model internals like a graph database, no GPU needed for browsing.
Supports patching and editing model knowledge without retraining or fine-tuning.
Features tiered context for infinite context and residual stream tracing capabilities.

Created 3 weeks ago

Updated 21 hours ago

Starred 1 day ago by

Marc Klingen(Cofounder of Langfuse).

thunderbolt by thunderbird

27875.0%

Control your AI: Choose models, own data, avoid vendor lock-in

Choose models, own data, and eliminate vendor lock-in for AI control.
Integrates local inference (Ollama, llama.cpp) and OpenAI-compatible model providers.
Cross-platform client deployable on-prem via Docker, Kubernetes, across desktop/mobile.
Targeting enterprise with production readiness, security audit, and dedicated support.

Created 8 months ago

Updated 17 hours ago

Starred 1 day ago by

Tim J. Baek(Founder of Open WebUI). Also starred by

Connor McArthur(Cofounder of dbt Labs),

Didier Lopes(Founder of OpenBB),

Thomas Dohmke(Former CEO of GitHub), and

4 more.

caveman by JuliusBrussee

96.7%

36k

Claude Code skill for LLM token reduction

Cuts LLM token usage by ~65% via a concise, caveman-like communication style.
Preserves technical accuracy and code integrity, removing conversational filler.
Offers adjustable intensity levels (Lite, Full, Ultra) for tailored brevity.
Leverages research showing brevity can enhance LLM performance and accuracy.

Created 2 weeks ago

Updated 3 days ago

Starred 1 day ago by

Elie Bursztein(Cybersecurity Lead at Google DeepMind). Also starred by

Travis Fischer(Founder of Agentic) and

David Cournapeau(Author of scikit-learn).

mcporter by steipete

3.1%

TypeScript toolkit for Model Context Protocol (MCP) integrations

Enables seamless TypeScript integration and CLI packaging for MCP servers.
Features zero-config discovery, typed client generation, and ad-hoc endpoint connections.
Automates CLI creation and generates strongly-typed TypeScript clients for AI agents.
Simplifies code execution workflows with a composable API and robust transport handling.

Created 5 months ago

Updated 2 weeks ago

Starred 1 day ago by

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

agent-skills by addyosmani

33.2%

17k

Production-grade engineering workflows for AI coding agents

Standardizes software development phases (Define, Plan, Build, Verify, Review, Ship) with structured, verifiable skills.
Integrates with AI agents via Markdown skills, enforcing best practices and quality gates.
Embeds Google engineering principles like Hyrum's Law, test pyramid, and Shift Left into agent workflows.
Skills include anti-rationalization tables and non-negotiable verification steps for robust agent output.

Created 2 months ago

Updated 1 day ago

Starred 1 day ago by

Tim Suchanek(Founder of expand.ai). Also starred by

Jeff Hammerbacher(Cofounder of Cloudera),

Wes McKinney(Author of Pandas),

Travis Fischer(Founder of Agentic), and

2 more.

emdash by generalaction

3.7%

UI for orchestrating parallel coding agents

Run multiple AI coding agents concurrently in isolated Git worktrees for compartmentalized task execution.
Centralized dashboard monitors agent progress and streamlines GitHub pull request creation and review.
Integrates Codex CLI and GitHub CLI, leveraging SQLite for local data persistence and privacy.
Extensible architecture planned for supporting diverse agents and custom workspace lifecycle hooks.

Created 7 months ago

Updated 1 day ago

...