ATLAS

Name: ATLAS
Author: itigges22

by itigges22

Verified

Adaptive Test-time Learning and Autonomous Specialization

2,064stars

182forks

Python

Added 7/21/2026

Installation

# Add to your Claude Code skills
git clone https://github.com/itigges22/ATLAS

Getting Started

Guides for using ai agents skills like ATLAS.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportVerified

Last scanned: 7/21/2026

{
  "issues": [
    {
      "file": "README.md",
      "line": 117,
      "type": "remote-install",
      "message": "Install command (remote install script piped to a shell — review the source before running): \"curl -fsSL https://raw.githubusercontent.com/itigges22/ATLAS/main/scripts/atlas-\"",
      "severity": "low"
    }
  ],
  "status": "PASSED",
  "scannedAt": "2026-07-21T06:27:22.521Z",
  "npmAuditRan": true,
  "pipAuditRan": true,
  "promptInjectionRan": true
}

README.md

Frequently Asked Questions

What is ATLAS?

ATLAS is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by itigges22. Adaptive Test-time Learning and Autonomous Specialization. It has 2,064 GitHub stars.

Is ATLAS safe to use?

Yes. ATLAS passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install ATLAS?

Clone the repository with "git clone https://github.com/itigges22/ATLAS" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is ATLAS written in?

ATLAS is primarily written in Python. It is open-source under itigges22 on GitHub, so you can review or fork the full source.

Are there alternatives to ATLAS?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh ATLAS against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

dstack claude-code

🌎 What is ATLAS?

ATLAS is a local coding agent that brings frontier-style reasoning and verification to compact open models. It puts more intelligence in the system around the model (planning, candidate generation, quality scoring, sandboxed testing, and repair) so smaller models can tackle real software work entirely on your own hardware, without a hosted API or per-token fees.

💡 Why ATLAS?

Get more from smaller models. ATLAS adds planning, candidate selection, verification, and repair around the model instead of depending on a single generation.
Verify before accepting. Generated code can be compiled, tested, and corrected inside an isolated execution environment.
Spend compute where it matters. Straightforward edits take a shorter path, while harder tasks receive more candidates, reasoning, and validation.
Run your own model. Use a compatible GGUF model on NVIDIA, AMD, Apple Silicon, Vulkan, or CPU-supported hardware.
Keep control local. ATLAS does not intentionally upload your repository or prompts to a hosted model or ATLAS-operated service. Sandbox commands have outbound network access by default; set ATLAS_SANDBOX_NET_INTERNAL=true to disable it.
Own the full stack. ATLAS is open source and self-hosted. It requires no hosted model or third-party model-provider API key; a local per-installation service token authenticates ATLAS services.

📰 Latest News

2026-07-06 - V3.1.3 "Maia" released - production-platform pass: staged upgrade/rollback with auto-restore, SQLite state store (no more Redis), signed artifact manifests, structured logs + correlation IDs, interactive permissions, session resume, and two adversarial bug-fix sweeps
2026-06-17 - V3.1.2 "Maia" released - broader hardware reach (ROCm / Metal / Vulkan), bring-your-own-model Lens + ASA training, in-the-loop lens retraining from your own workloads, and an agent-reliability pass
2026-05-12 - V3.1.0 "Maia" released - native Bubbletea TUI, one-command bootstrap, streaming Lens + ASA activation steering, AST-aware surgical edits
2026-03-26 - Hacker News front page - 489 points, 285 comments
2026-03-05 - V3.0 released - 74.6% LiveCodeBench pass@1-v(k=3) on frozen Qwen3-14B (pass@1 with k=3 generated candidates, Lens selection, and repair - not single-generation pass@1; methodology)
2026-02-18 - V2.0 released - benchmark infrastructure, HumanEval/MBPP/LiveCodeBench/GPQA/SciCode evaluation suite

⭐ Star History

Updated weekly (Mondays, via GitHub Actions).

🧱 What ATLAS Does

atlas-tui - native Bubbletea terminal UI; the canonical chat client. Type atlas in any project directory to launch it.
- Live pipeline view - watch V3 stages stream in a side pane
- Slash commands - /add, /diff, /commit, /run for local file context and shell-out
- Input modes - chat, !bash, and /slash with a hint dropdown
atlas-proxy - Go agent loop that orchestrates the system.
- Tool-call routing - classifies file operations by complexity tier
- Grammar enforcement - GBNF schemas strongly steer output toward the expected JSON shapes, with proxy-side recovery for malformed or truncated output
- BiasBusters - four composed mitigations (descriptions, grammar bans, system notes, ASA steering) that push the model toward ast_edit for structural code edits
- Safety limits - turn caps, token budgets, timeouts
V3 Pipeline - multi-phase code generation; turns a single prompt into a verified candidate.
- PlanSearch - constraint-driven structured planning
- DivSampling - diverse candidates across temperature and strategy
- Budget Forcing - per-phase thinking-token allocation
- PR-CoT Repair - self-generated test cases for iterative fixes
- Refinement Loops - sandbox verify and correct, then repeat
- Derivation Chains - multi-step reasoning for harder problems
Geometric Lens - energy-based scoring over the model's own embeddings, no external oracle. (What is a "Geometric Lens"?)
- C(x) Cost Field - model-hidden-dim→512→128→1 MLP that scores candidate quality
- G(x) Quality Prediction - XGBoost ensemble used for selection
- RAG / PageIndex V2 - AST-aware code retrieval and project indexing
- Confidence Router - Thompson Sampling routes compute to the candidates that need it
Sandbox - isolated execution for build verification.
- Multi-language execution: Python, Rust, Go, C, Shell, others
- Compilation and linting before scoring
- Runs both generated and existing test suites
llama-server - local LLM inference on one consumer GPU.
- GPU-accelerated quantized inference (Q6_K / Q4_K_M) - NVIDIA CUDA, AMD ROCm, Apple Metal (macOS hybrid), and Vulkan; Intel SYCL on the roadmap
- Grammar-constrained decoding at the token level
- Self-embeddings, so the lens doesn't need a second model

Full documentation (setup, architecture, configuration, troubleshooting, benchmark reports, and the research behind each component) lives in the docs/ directory.

🚀 Get Started

One-shot install:

curl -fsSL https://raw.githubusercontent.com/itigges22/ATLAS/main/scripts/atlas-bootstrap.sh | bash

Prefer not to pipe a moving script into bash? Same installer, two more careful ways to run it:

# Pinned to a release: script, checkout, and images all at the signed tag
curl -fsSL https://raw.githubusercontent.com/itigges22/ATLAS/v3.1.3/scripts/atlas-bootstrap.sh \
  | ATLAS_BOOTSTRAP_REF=v3.1.3 bash

# Review before running
curl -fsSL -o atlas-bootstrap.sh https://raw.githubusercontent