Search

Azure DevOps desde la terminal: work items, trazabilidad y contexto autodetectado del git remote

`@lumina-web/canvas-agent` contains the bridge modules used by the installed Lumina runtime. The normal Lumina Canvas plugin invokes the installed runtime instead of this development command.

A framework for iterative code generation for ML and data analysis tasks using parallel LLM agents in Colab.

Provenance-aware execution security for DeepSeek Harness. Track sensitive data across tool calls and stop risky side effects before execution.

TypeScript SDK for agents and scripts to interact with the CoinSpace on-chain social protocol directly -- no API, no server, bring your own wallet.

Self-improvement loop for Hermes Agent: reads its own trajectory, proposes and applies the smallest skill/memory edit (create/patch), journaled with rollback. /refine command, refine_run tool, on_session_end hook.

Deterministic premise invention and hypothesis generation without LLMs.

Official Python SDK and fleetctl CLI for OpenAgentFleet — self-hosted autonomous computer-use agents, each with its own Linux desktop

Forensic reconstruction for AI agent security incidents (local-first, standards-aligned, defensive DFIR).

Skill-pack giup AI coding agent code ky luat hon, xay dung hoan toan tren dien thoai.

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...

AutoKnit — divide-and-conquer PRD execution framework: PRD in, stable maintainable code out. Program does the scheduling (0 token), LLM only thinks.

LLM-grounded UI coordinate finding for Autourgos computer-use agents — locates a described UI element in a screenshot and returns its position normalized to a 0-1000 scale (Gemini computer-use's coordinate convention).

X out the AI behavior you never want again - cross out wrong agent behavior, keep the rule, plug it into Claude Code, Codex, OpenCode, Gemini CLI, Copilot, pi, Kiro or any AGENTS.md reader

Multi-agent collaboration board UI: toggle + agent/topology editors + resizable-font agent windows + topology diagram

Self-hosted, git-backed CMS agent, distributed as a compiled npm package.

Local-first trace analysis and diagnostic engine for multi-agent LLM systems.

Agentic Control Plane for fx (vercel-labs/fx) — a governed protocol middleware for fx's Agent Client Protocol mode, checking every tool call against your policies before fx's own permission prompt reaches the client.

This model always redirects to the latest model in the GLM Flash family.

A CAN / J1939 / UDS / DoIP protocol parsing gateway with state tracking and RAG diagnostic agent