Search

A lightweight, framework-free Augmented LLM Agent powered by LLM + MCP + RAG

Individualized worksheets for educational and therapeutic professionals from a support goal, level, and age — local LLM agent workflow, bring-your-own ICF references; a material generator, not a therapy program

Azure Container Apps Sandboxes as a sandbox backend for Microsoft Agent Framework agents — reference implementation of agent-framework#7568.

Sandboxed Bicep validation (bicep build + bicep lint) as a Microsoft Agent Framework tool — reference implementation of agent-framework#7568 — written against maf-sandbox so it runs on any sandbox backend.

Shared contract for the MJML agent editor: document addressing, stable IDs and tool schemas.

Agent Memory File System - a local-first memory store for AI agents, with semantic search.

Proof-carrying memory for any agent framework — gate memory before generation, get an Answer Receipt. Adapters for LangGraph, the OpenAI Agents SDK, and anything else.

Get every job posting from any Workday careers site: titles, locations, posted dates, pay ranges, and apply URLs as structured items. Apify-backed n8n community node, pay-per-result, and usable as an AI agent tool.

Delegate tasks to specialized subagents with isolated context windows.

AI Traffic Control — local-first CLI to inspect and govern AI agent traffic on your machine

Generate contrastive datasets for detecting unsupported assumptions in LLM agents

Autonomous offensive-security agent: recon, authorized pentest, vuln hunting, DFIR & multi-framework compliance from a single prompt. Local-first (llama.cpp), skill-based, deterministic-first.

Plain-English observability for AI agents — live dashboards, replay, and one-line LangGraph auto-instrumentation, metadata-safe by default.

AgentPhone Python SDK — give your AI agents phone numbers, SMS, and voice calls

AIPost.email tools for CrewAI — structured AI agent messaging with Ed25519 identities

LLM-assisted OpenModelica modeling: a tested agentic generate-compile-simulate-verify loop with structured omc diagnostics, quantitative trajectory verification, and a benchmark task ladder.

Real-time message bus for Claude Code sessions — one asks, another wakes and answers, hands-free.

Generic, language-agnostic AI-assisted development workflow for OpenCode — pipeline, agents, standards, and scripts

basically free forever vibecoding

Workflows are Just Lists. Progressive reading DSL for structuring LLM interactions.