Tag

Agent Governance Toolkit

Performs deterministic, sub-millisecond policy checks on every agent action (allow/deny + audit) and adds zero-trust identity, execution sandboxing, and SRE features. Covers the OWASP Agentic Top 10 and is designed to sit between agent frameworks and runtime actions for auditable, low-latency governance in production.

OBLITERATUS

Identifies and surgically removes the internal activation directions that trigger refusal behavior in large language models, with one-click options on a HuggingFace Space or a local Python API. Combines multiple extraction methods (SVD, whitened SVD, sparse autoencoders), reversible steering, and analysis-informed verification to quantify capability and refusal trade-offs.

whichllm

Detects your GPU/CPU/RAM and ranks HuggingFace models that will actually run and perform best on your machine, using live, recency-aware benchmarks and a one-line CLI for simulation, planning, and instant local runs.

ShadowBroker

Aggregates 60+ real-time OSINT feeds into a self-hosted geospatial dashboard and exposes an HMAC-signed agentic AI command channel so LLM-driven agents can query and act on live telemetry; privacy is experimental.

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.

CLI-Anything

Automatically converts codebases into structured, JSON-first CLI harnesses so LLMs and AI agents can reliably control desktop and server software; includes a CLI-Hub registry, demo harnesses, and agent plugins for one‑command generation and installation.

BugHunter

Terminal-first toolkit that automates bug bounty workflows — recon, hunting across 20 vulnerability classes, validation, and submission-ready report generation; runs as a Claude Code plugin or standalone CLI with support for free local AI providers (Ollama, Groq, DeepSeek).

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.

ARIS (Auto-claude-code-research-in-sleep)

Lightweight, Markdown-only skill pack that lets LLM agents autonomously run ML research workflows—literature survey, idea discovery, cross-model review loops, experiment automation and paper writing—designed for Claude Code, Codex CLI, Cursor and local model setups.

TAAC2026 Demo Dataset (1000 Samples)

Provides a 1,000-row sample user–item interaction Parquet for the TAAC2026 recommendation task, using a flat column layout with 120 top-level columns (IDs, labels, user/item int & dense features, and four-domain behavioral sequences). Updated 2026-04-10.

AutoResearchClaw

Turns a single research idea into runnable experiments and a conference-ready paper by orchestrating an LLM-driven end-to-end workflow (literature → design → code → sandboxed runs → analysis → writing). Provides human-in-the-loop checkpoints, domain-specialist executors, and multi-layer citation verification.

Needle

A distilled 26M-parameter encoder–decoder LLM for on-device function-calling and tool use. Uses a pure-attention Simple Attention Network, provides open weights and local finetuning, and targets high-throughput inference on the Cactus runtime.