An agent skill that plays ARC-AGI-3. One rule: say what an action will do before you spend it. Claude Code on Opus 5 finished all 25 public games at 100.00 RHAE in 7,645 actions.
☆89Oct 28, 2026Updated last week
Alternatives and similar repositories for arc-skill
Users that are interested in arc-skill are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- such framework. very agent. much deploy. Агент ведёт фичу от идеи до прода. Человек занимается инженерией, а остальное сделает автоматика☆28Oct 30, 2026Updated last week
- ☆12Oct 9, 2025Updated last year
- Breaking the quadratic memory barrier in AI☆60Oct 13, 2026Updated 3 weeks ago
- AI Paints Whatever You Want!☆30Sep 23, 2026Updated last month
- ChatGPT like interface for Pakistan Stock Exchange financial filings.☆14Aug 10, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Fermion Research fork of llama.cpp: FV5/FV5B five-value ternary types for Neutrino GGUF packs (CPU + CUDA)☆14Sep 29, 2026Updated last month
- Local autonomous AI agents with live Fish/XTTS voice, Codex Fast mode, memory, desktop tools and a fullscreen Telegram Mini App. Portable…☆15Updated this week
- OpenAI-compatible HTTP API that acts as a gateway to the Agent Client Protocol (ACP)☆19Sep 17, 2026Updated last month
- ☆146Aug 12, 2026Updated 2 months ago
- Hybrid lexical + AST graph code search☆14Oct 30, 2026Updated last week
- AppMap client agent for Node.js☆13Updated this week
- Local Figma Desktop plugin and localhost bridge for AI-ready design handoff bundles, without Figma API, Dev Mode MCP, or access tokens.☆17Aug 11, 2026Updated 2 months ago
- AI агент, который живёт в Telegram чатах (личный, семейный, публичный)☆28Updated this week
- ☆44Apr 14, 2026Updated 6 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- DracoLure — Dragon Vector Honeypot: polyglot deception honeypot with real-time detection, threat scoring, and quarantine.☆19Jul 28, 2026Updated 3 months ago
- An open recursive self improvement agent☆53Aug 13, 2026Updated 2 months ago
- Claude Code skill — autonomous ML intern (port of huggingface/ml-intern) with Telegram + Slack notifications☆67Jun 10, 2026Updated 4 months ago
- Zaxy turns agent work into durable, auditable memory: a hash-chained Eventloom log as the source of truth, an embedded temporal knowledge…☆17Aug 10, 2026Updated 2 months ago
- Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions…☆522Updated this week
- AI-разметка видео (главы/хайлайты/субтитры/HLS) одной командой поверх NeuralDeep Hub. Скилл для Claude Code и Codex.☆16Jul 24, 2026Updated 3 months ago
- Fugusashi — Federated Learning of LLM Routing with Human-Interpretable Decisions. Open-source alternative to Sakana AI Fugu.☆23Aug 6, 2026Updated 3 months ago
- A RAG system that attempts to eliminate relationship hallucinations by fusing a knowledge graph with a vector DB and prioritizing knowled…☆10Apr 10, 2026Updated 6 months ago
- MCP Server to run python code locally☆54Dec 4, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A compiler for LEGO® models, built for AI agents.☆19Oct 30, 2026Updated last week
- Turn your coding-agent sessions into private evals and find the cheapest setup that still solves your tasks.☆79Oct 14, 2026Updated 3 weeks ago
- Public repository for MirrorCode☆81Sep 15, 2026Updated last month
- Your best ideas don't spread on their own. This plugin gives you the science-backed playbook to design, launch, and defend how ideas move…☆19Apr 27, 2026Updated 6 months ago
- ARC-AGI-3 Milestone 2 solution built on Tufa Labs’ Duck harness, with improved agent tools, compute scheduling, and SGLang serving.☆17Sep 30, 2026Updated last month
- A Codex skill that keeps human outcomes and creative intent ahead of overengineering.☆55Aug 13, 2026Updated 2 months ago
- A self-hosted drop-in replacement for TypeSafe's jev, powered by GliFormer.☆312Sep 20, 2026Updated last month
- Home of the SanityHarness Leaderboard website.☆22Oct 24, 2026Updated last week
- Jev-style decision-model training reproduction on MiniCPM5-2B (stage 1: single-letter Choice classification)☆21Oct 22, 2026Updated 2 weeks ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Simple meeting diarization and speaker id assistant for meetings.☆12Feb 10, 2025Updated last year
- Bounded, inspectable LLM inference pipelines from declared YAML — runs offline against Ollama or any OpenAI-compatible local server, emit…☆46Jul 7, 2026Updated 4 months ago
- ☆18Dec 24, 2025Updated 10 months ago
- ☆40Sep 4, 2026Updated 2 months ago
- Truthful scheduler-step and streaming visualization for local LLM inference☆35Sep 6, 2026Updated 2 months ago
- Visual debugging, execution traces, and observability for AI agents.☆25May 1, 2026Updated 6 months ago
- Epistemological database for agent and human efforts, beliefs, and findings.☆125Updated this week