Search

Policy enforcement and observability for LLM agents. Zero code changes.

Tilth — minimal long-running agent harness against any OpenAI-compatible endpoint. Brain/Hands/Session split, Ralph loop, four memory channels.

Superserve sandbox integration for Deep Agents

A natural-language shell agent powered by Claude, OpenAI, or Gemini.

Runtime firewall for AI agents - blocks catastrophic tool calls and self-heals the run.

A lightweight terminology memory layer for AI agents.

Carry an AlgoVoi keystone decision into a LangChain run trace: a recomputable execution_ref under algovoi.keystone.*, verifiable offline

Free, open-source observability for AI agents. Trace LLM calls, catch silent failures, score output quality.

MCP server connecting AI agents to ITASCA PFC — run DEM simulations through natural conversation

Evaluate LLMs against behavioral specifications (AGENTS.md, Claude.md, custom rules)

Plain-text memory for AI agents — small, filtered, compressed, self-pruning. No database, no embeddings, no dependencies.

LangChain integration for Agent Passport — wrap tools with passport authorization

Batteries-included helpers for building LLM-powered apps with the Vercel AI SDK and OpenRouter — automatic cost/usage tracking and pretty stream logging out of the box.

CLI tool for building AI agent workflows

Persistent memory MCP server for AI agents — 13 tools, semantic search, knowledge graph, on-device SQLite

Declarative AI-agent framework — composable agents, multi-agent orchestration, and a protocol-decoupled server

Official TypeScript SDK for Couplet Agent Runtime — ACS v1, types, clarify helpers, HTTP client

Agentic Platform agent client contract and routing manifest capability

Agentic Platform reusable validation capability package

Agentic Platform SDLC seed bundle provider package