Search

Check an LLM request against provider rules before you send it. Offline, deterministic, no API key.

Root-cause vs symptom discrimination for UAV telemetry: a realtime detector tier and an evaluation harness for LLM agent judges.

CrewAI tools for Zillapi: look up Zillow property data, valuations, schools and listings from CrewAI agents.

A runtime circuit-breaker for the Degeneration-of-Thought (DoT) problem in multi-agent LLM systems.

Free, local AISI S100/S240/S400 cold-formed steel design agent: your LLM + OpenSees + stamped-style reports

CrewAI tools for StayingAPI: search stays, check availability, price a stay, compare prices across booking sites and read reviews, from CrewAI agents.

A governed coordination ledger for local multi-agent fleets: provenance typing, a promotion gate, an instruction-boundary envelope, and a retention invariant — with an executable conformance suite that proves them.

Context retrieval and injection for AI-agent runs.

Trajectory evaluation, LLM judges, and a pytest plugin for Pyantra.

Profile-conditioned author style transfer for LLM agents

BalancedMultiDimensionMemory — a LangGraph AgentMiddleware for long-term LLM memory (Ebbinghaus decay + RAG staging + user profile consolidation)

AI model: AyoubChLin/lfm2.5-2.6b-fable5-coding-agent

AI model: limnmn/Qwen3.5-4B-AgentTools-GGUF

Zeline — an open-source agentic AI framework developed by Zerolinear.

Agent-native CLI for Adobe InDesign automation — 150 tools, HTML ↔ InDesign conversion, and structured JSON returns built for AI agents.

Playwright + TypeScript automation framework for UI/API testing with Page Object Model, shared fixtures, reusable services, local agent skills, and an AI-ready codebase second brain

Lightweight context-aware agentic api scanner & tester directly in your terminal

Your agents don’t hand off the work. Kungfu keeps the same Work moving across Codex, Claude, OpenCode, and your own execution surface.

Equaxis: a governed, observable and reliable agent runtime powered by Pi.

AI code review with DeepSeek: headless PR review automation that verifies PR descriptions claim-by-claim against real code, checks docs against reality, flags requirement impact, human-in-the-loop + auto review poller + web dashboard