Search

The Fintech Builder algorithm library — canonical, cross-language reference implementations of market-data, corporate-action, index, breadth, candlestick and technical-indicator algorithms, exposed as provider-agnostic subpath modules.

Let Claude Code generate images. An agent skill + text-to-image CLI that turns Google's Antigravity CLI (agy) into an AI image generator — hero art, icons, illustrations, textures — from Claude Code or your terminal.

Automatic and agent-friendly data preprocessing tool for LLMs and ML.

A CHAP-aligned, local-first toolkit for capturing, validating, governing, and retrieving tacit fragments as governed tacit memory for AI agents.

Open source evaluation toolkit for LLM pipelines and agents

One AI agent, everywhere you work — terminal, desktop, mobile, and your chat apps. Rust core. 3,800+ models.

Portable JSON memory for LLM agents. No vector DB, no embeddings, any provider.

Tacnode integration for LangChain and LangGraph — multi-modal retrieval and a drop-in agent stack on one hybrid SQL plane

The 14-phase Engineering Influence content pipeline (thesis → book → novel → screenplay → AI film → distribution) as six Claude Code Agent Skills

Agent Skills for vibe engineering — 71 evidence-grounded practitioner references as a Claude Code plugin marketplace

Janet builds and maintains portable LLM wikis in plain Markdown using OKF.

Scaffold an AIOS agent package (npm create @aios-platform/agent)

Understand what your AI agents think about you

JCKW-AGENT: AI CLI Terminal Interface by prastya-dev, powered by Google Antigravity

harness-neutral Constructive database tools — provisioning, schema, policies, records, templates and codegen as HarnessTools any adapter can bind

Deterministic record/replay debugger for LLM agents: replay a failed run offline, instantly, for free

Agent-plane presentation selector: composes one agent's tools as Code Mode, native, or both

Run your own agents inside Redline AI experiments — from your repo, with `redline dev`.

See what every plugin puts into the model.

Hesperus — Autonomous IoT Visual Monitoring: an LLM agent turns plain-English goals into capture schedules, sends them over MQTT to a bare-metal STM32U5, and analyzes frames with cloud and self-hosted VLMs. Originally built as a Bachelor thesis (Maastricht University): 6-backend VLM benchmark + a cross-provider t=0 constraint-drift finding.