Client SDK for the Tangle Sandbox platform - build AI agent applications with dev containers
MoltNet agent runtime — coding-agent-agnostic Task execution loop
Open-source command center for governed AI coding agents with built-in onboarding, hard gates, MCP, and shareable run receipts.
OpenInference instrumentation for AWS Bedrock Agent Runtime
Harness-aware Claude Code and Codex CLI extension for pi
Local agent runtime reporter for the OCTO platform — detects installed AI agent CLIs (Claude Code, OpenClaw) and reports status. This package resolves the prebuilt Go binary from the matching platform sub-package; no postinstall download.
Local AI control plane with a resident private assistant for task execution and a unified model proxy API for Claude Code, Codex CLI, Gemini CLI, OpenClaw, accounts, API keys, logs, and usage.
TypeScript SDK for Weavz governed app access APIs
Topic consumer and agent runtime package for KalamDB
Standalone Azad agent runtime CLI.
Pluggable adapter seam for supervising whatever actually runs an agent — the Claude Agent SDK, OpenAI Agents, the Vercel AI SDK, a plain subprocess, and more. Lets a host swap agent runtimes without hardcoding any framework into its dev loop.
efferent — an agent runtime on Effect.ts + Bun. One CLI to run agents: an interactive TUI, headless (print/json/rpc), or a persistent per-workspace daemon that thin clients attach to. Multi-provider (Anthropic/OpenAI/Gemini), persistent sub-agent context
Starts, stops, and monitors the embedded Eliza agent runtime.
Paybond Kit for TypeScript: agent spend governance for paid tool calls with spend authorization, evidence receipts, refunds, disputes, hosted Gateway sessions, and settlement.
Production-ready TypeScript agent framework built on LangGraph with orchestration, middleware, and typed abstractions.
In-process agent execution runtime for Pi — unified execute entry, isolated state, sync/background modes
Open-source coding-agent harness you can actually change — own the loop (prompts, gates, routing, skills, terminal states), use any model, run long tasks while you're away.