ComposioHQ/composio
Composio provides SDKs for building AI agents capable of interacting with over 1000 tools, offering capabilities like tool search, context management, and authentication across various AI frameworks.
Awesome Infra for AI › Workflow Orchestration for AI
sandbaseai/sandbase-harness
SandBase Harness is a runtime layer for operating AI agents, aimed at the gap between a model SDK and a production deployment. Agent SDKs handle the model loop; what they do not provide is persistent sessions, tool governance, sandbox boundaries, credential handling, memory, auditability and a human-facing interface for inspecting what happened. Harness supplies those. It exposes a Claude Managed Agents-style /v1 API alongside a local console, and stores agents, sessions, environments, credential vaults, memory stores, files, skills and API keys in SQLite by default, with file and skill bytes kept in a workspace state directory. Generated code runs inside a sandbox, and four backends are offered: a local process, per-session Docker containers, Kubernetes via exec and copy, and a self-hosted worker queue. Sessions emit resumable server-sent events, so a long-running agent can be replayed and debugged after the fact rather than watched live, and the console shows the same history to a human reviewer. Tool access is governed through MCP toolsets, permission policies, built-in tools and skill packages, with approvals for sensitive calls. Model providers are pluggable — OpenAI, Anthropic and OpenAI-compatible endpoints — but a workspace commits to one active provider boundary, configured through a settings system with validation and both form and JSON editing. A bridge over MCP stdio lets the runtime be driven as a plugin from another harness, covering agents, sessions, streamed turns, artifacts and cancellation. It is written in TypeScript, requires Node 22 or newer, ships a TypeScript SDK, and is explicitly local-first: no hosted control plane is required and all state stays in the operator's infrastructure.
https://github.com/sandbaseai/sandbase-harness
Also in Workflow Orchestration for AI
TencentCloud/TencentDB-Agent-Memory
TencentDB Agent Memory is a memory management system for AI agents, featuring a 4-tier progressive pipeline to improve efficiency and reasoning by categorizing and condensing agent memories without...
TransformerOptimus/SuperAGI
SuperAGI is an open-source framework designed for building, managing, and running autonomous AI agents, offering tools for deployment, capability extension, and performance monitoring.
dataelement/bisheng
BISHENG is an open LLM application DevOps platform focusing on enterprise scenarios, providing comprehensive features for GenAI workflows, RAG, agents, model management, evaluation, and enterprise-...
iflytek/astron-agent
Astron Agent is an enterprise-grade platform for building, orchestrating, and deploying AI agent applications with integrated RPA, model management, and high-availability features.
0xPlaygrounds/rig
Rig is a Rust library designed for building modular and scalable LLM-powered applications, offering a unified interface for multiple model providers and vector stores.
plastic-labs/honcho
Honcho is a memory infrastructure for building stateful AI agents, enabling them to understand and retain information about people, agents, groups, projects, and ideas over time.
julep-ai/julep
Julep is an open-source platform for building, orchestrating, and self-hosting agent-based AI workflows with persistent memory and tool integration.