Tag

Squad

Creates human-directed teams of AI agents (via GitHub Copilot) that live in your repo, persist knowledge, and coordinate development work. Key features: repo-first persistence, watch/triage automation, and an extensible CLI/SDK — alpha software, Copilot-dependent.

Ultra-FineWeb-L3

Provides L3 refined synthetic training data by converting high-quality web corpora into Q&A pairs and multi-style rewrites; supplies 400B+ English and 200B+ Chinese tokens for late-stage LLM pretraining and decay-phase training.

OpenAI/parameter-golf

A challenge repository for training the best language model that fits inside a 16,000,000‑byte (16MB) submission artifact; provides baseline training code, FineWeb bpb evaluation, a public leaderboard, and compute-grant instructions for short 8×H100 runs.

Shannon — AI Pentester by Keygraph

Autonomous white-box AI pentester for web apps and APIs. It reads your source code, maps the running app, then runs specialized agents that fire real proof-of-concept exploits for injection, XSS, SSRF, and auth flaws — reporting only what it can exploit.

JobOps

Find and rank jobs across major boards, auto-tailor a resume per role using an LLM-driven pipeline (RxResume v4), and track application emails — all as a self-hosted Docker pipeline for privacy-conscious users.

Agent Teams

Desktop app that orchestrates teams of AI agents: agents autonomously create, assign, and complete tasks while messaging and reviewing each other on a Kanban board. Includes local/no-auth models, provider runtime auto-detection, per-task logs, and hunk-level code review.

Anthropic Cybersecurity Skills

Provides a structured library of 754 cybersecurity skills (agentskills.io format) mapped to MITRE ATT&CK, NIST CSF, MITRE ATLAS, D3FEND and NIST AI RMF — so AI agents can load practitioner workflows and decision logic across 20+ platforms.

autoresearch

Lets an LLM autonomously propose, edit, run, and evaluate short single‑GPU LLM training experiments — fixed 5‑minute runs (~12 experiments/hour). Agent edits a single train.py; humans supply goals via program.md. Single‑GPU, val_bpb metric.

Hermes Agent Self-Evolution

Automatically evolves Hermes Agent skills, prompts, tool descriptions and code using DSPy + GEPA — mutating text via API calls, evaluating trace-based failures, and selecting variants that pass tests and human PR review. No GPU training required; runs cost roughly $2–$10 per optimization.

Agent-Native

Framework for running agents inside real applications — it exposes shared actions, SQL-backed state, tools, skills, jobs and UI surfaces so agents can act on app state instead of just chatting. Backend-agnostic TypeScript stack with cloneable app templates and visual planning/recap features.

claude-plugins-official

Curated marketplace of Claude Code plugins maintained by Anthropic, separating its own internally built plugins from vetted community submissions. Browse and install directly inside Claude Code via /plugin install {name}@claude-plugins-official.

Articraft

Transforms articulated 3D asset creation into a programmatic, LLM-driven code-generation workflow that produces objects with semantic parts, robust geometry, and physical joints. Includes CLI generation, a local viewer, and pipelines for large-scale dataset contribution.