Trending AI repositories
Tracked daily across the agentic ecosystem. Velocity is computed from our own snapshot history — collecting the first week of data now; repos are linked to the startups behind them.

A Simple Baseline for Video World Models with Memory

Claude Code / OpenClaw skills for Google Maps lead generation. Scrape businesses, extract emails, analyze competitors, write cold outreach — powered by gmapsscraper.io API.

Local-first AI workspace for macOS. Ten workspaces — Coder, Agent Swarm, Finance, 3D Forge, Sandbox, Virtual OS and more. 12 providers, or fully offline with Ollama. No backend, no telemetry, no account. Your keys and files stay on your machine. 8.9 MB, MIT.

Federation over Text (FoT) is a federated-learning-like paradigm for multi-agent reasoning.

An ongoing, collaborative meta-analysis about Human-AI-Interactions. We aggregate data and knowledge to build a non-abrasive, user-friendly prompting framework tailored to LLM mechanics, ensuring reasoning stability and a friction-free prompting environment that is safe for the human psyche and wellbeing.

GitHub as a knowledge graph for AI agents. Autonomous dev pipeline for Claude Code - investigate, build, review, merge. Issue in, PR out.

Automotive Agent Protocol

Automate viral reel/tik-tok videos via AI multi-agent system. ~$0.1/reel.

Expert-thinking AGENTS.md profiles that teach AI agents to reason like senior scientists and engineers.

Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs

Don't be the 40%. A production-ready blueprint for governing autonomous AI agents in IT operations — with executable policies, typed tool contracts, ISO 42001/NIST AI RMF mapping, and a 4-level maturity model. Vendor-neutral.

Edit Videos and Design Images with Claude code or Codex

Stop re-explaining yourself

SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.

Fixing GRPO training collapse in long-horizon multi-tool agents. A lightweight PRM-Lite + LATA joint approach achieves +37% over vanilla GRPO on τ-bench airline (50-task, multi-turn).

Real-time gamified dashboard for monitoring Claude Code and Codex AI agents in a medieval fantasy setting

CoDA-Bench is a benchmark for code agents on data-intensive tasks. 🎈代码智能体能搞定数据密集型任务吗?

Matrix is the cognition and UX layer on top of Paxeer Network. It turns natural-language requests from non-developers into a typed, inspectable, correctable Intent IR

The first open-source @base agent.

An AI workforce platform: role-specialized agents with multi-provider LLM, MCP, tasks, and a web + CLI UI. You're in charge.

Turn Claude Code into an equity-research agent: 24 analysis skills (Anthropic's open-source bundle + community), a single data MCP, and a personalization layer for investors at any level.

Copilot-style AI coding agent for VS Code, powered by DeepSeek V4.

Self-hosted AI workspace built around context management. Works solo, scales to teams.

This is an attempt to make original open mythos better with chat ui.

Continuum — the agent runtime by ShyftLabs. Build, orchestrate, ship.

A curated list of public-source, research, and commercial tools for AI security and AI-assisted cybersecurity — autotriage, agent security, AI/ML supply chain, pentest agents, AI SAST, LLM-driven fuzzing, threat intelligence, SOC/SIEM triage, reverse engineering, LLM red-teaming, and more.

TRINITY in Elixir (An Evolved LLM Coordinator): route LLM calls via a small-model hidden-state router + Axon coordination head, with Thinker/Worker/Verifier orchestration and policy loop for acceptance-driven completion.

Annotate any page in Chrome and send the screenshot, selected element metadata, and your instruction directly into OpenCode.

Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and reviewable automations. Local memory; local or cloud models

A modular UX, design, and product optimisation system for turning AI-built interfaces into production-grade apps, turning proven principles into enforceable constraints that reduce friction, build trust, and drive action. Works with Claude, Codex, Cursor + all other agentic AI models.