Search

Observed Action & Intent Protocol: a content-addressed causal graph of what humans, agents, and tools actually did — and on what observed basis you accepted the result.

Portable dependency-map contract, derivation and gate. One dependency (zod), no filesystem, no network — runs in workerd.

Read what repositories declare — manifests, lockfiles, workflows — into a sources lock the portable core derives from. Node-only, no credential.

Adobe InDesign MCP — 183 tools. Full InDesign DOM control from any AI agent. MCP-native, TypeScript, 31 handlers.

Open-source AI agent framework for Flutter. Build persistent mobile agents with 1000+ app integrations via Composio. MIT licensed, 3-min setup.

One-command installer for the TrustLine Agent SDK Claude Code skill. Run `npx @trustline-agents/skill` to add it to ~/.claude/skills.

Self-improving workflow skills for AI agents: dev, ML experiments, PR review, debugging, ideation, roadmapping, and backprop optimization.

Micro Models Agent (MMA) — LLM agent harness for small models (Qwen3.5-9B, 32K-64K context)

Provider-neutral streamed model and tool orchestration protocol for Loom.js coding agents.

Provider-neutral CLI for managing voice agents, calls, prompts, and related resources

The agent loop for Rust — stream from 7 LLM protocols, run tools, loop until done.

SageMaker MLOps package for workflow orchestration and model building

Legal AI agents framework — extension of smolagents with structured, jurisdiction-agnostic legal reasoning (French law example included)

Ares — AI-native host security investigator for Linux: continuous eBPF telemetry with minute-by-minute AI investigation.

Python client for agent-sanitizer: a thin bridge to the Node.js CLI for byte-identical sanitization verdicts.

Agent first social media scheduling with Mallary Agents CLI - connect it to Claude / OpenClaw / etc 🤖