Search

Capacity-bounded warm memory for LLM agents, with a LangGraph BaseStore implementation, embeddings-based importance scoring, and a comparative benchmark.

🎵 Type a vibe, get a Spotify playlist. Zero hallucinated tracks. Powered by Claude + OpenAI. Runs 100% locally.

Cognitive commitment engine with constitutional safety. Watches your messages for promises ('I'll send that Monday'), remembers them, and follows up without judgment. Goes quiet when you're depleted. Deterministic core (Patent P1) + optional Claude Opus 4.7 nuance.

AI-driven workbench for computational materials science — interactive 3D structure viewer, natural-language CatBot assistant, visual DAG workflow engine, HPC job submission. Tauri desktop app with SvelteKit frontend and FastAPI Python backend. Drives VASP, ORCA, CP2K, QE, GPAW, DFTB+, SIESTA, LAMMPS.

Wiki Game LLM agent built on AISI Inspect.

Deterministic task lifecycle enforcement for multi-agent systems

Universal tool-calling wrapper for non-tool-native LLMs — emulates function calling via structured JSON planning

End-to-end AI agent workflow that turns a one-line product brief into a market-grade React app against any design system. Drop-in skill for Claude Code, Cursor, OpenCode, Gemini CLI, Trae, Windsurf, Kiro, and Aider.

ALLOW SDK for TypeScript — network-layer interception for AI agent authorization

CLI tool to interact with condensed JSON project snapshots for humans and AI agents

JavaScript SDK for the Agent2Agent (A2A) Protocol - enabling communication between AI agents

Structural code reader for LLM agents — Read, with zoom levels.

Python SDK for Grain — a structured data format for describing AI agents.

Developer SDK for building personalized voice AI assistants

Python SDK for Agent Berlin - AI-powered SEO and AEO automation

GridFleet agent — runs on each host

Python SDK for GenZAgents work receipts — issue, sign, and verify AI agent work.

Self-contained knowledge retrieval engine — hybrid search, entity graph, temporal reasoning, session briefing

Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and operational efficiency. It is optimized for coding agents, tool...

Multi-agent CLI that answers questions about your database and runs code in a sandbox.