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
ai-sdlc-framework/ai-sdlc
AI-SDLC calls itself the "Decision Engine" for spec-driven AI workflows: the execution-and-governance half of a spec-driven development stack, picking up where front-of-funnel spec tools (e.g. GitHub Spec Kit) leave off and carrying a task from an agreed contract through to a shipped, reviewed change. It is built around five pillars. A Definition-of-Ready gate blocks dispatching any task whose key decisions the operator has not actually made, with a planned Decision Catalog to rank and route open questions. An autonomous pipeline orchestrator (`cli-orchestrator tick`) walks the task dependency graph, applies admission filters, dispatches admitted tasks into isolated git worktrees, and runs a fixed pipeline — a developer subagent, three parallel reviewer subagents, attestation signing, and pull-request creation — quarantining failures and resuming from checkpoints after interruption. Cross-harness review enforces, by construction, that the harness which implemented a change (say, Claude Code) cannot also serve as its reviewer; DSSE-signed attestations record which harness performed each role so a different harness (say, Codex) must independently review the work. An operator TUI surfaces pending decisions, pipeline and PR status, the dependency graph, configuration, and analytics in one terminal interface. Finally, declarative governance resources (Pipeline, Decision, AgentRole, QualityGate, AutonomyPolicy, AdapterBinding), defined with JSON Schema, let teams run quality gates as advisory, soft-mandatory, or hard-mandatory, and derive gate defaults from compliance postures such as the EU AI Act, NIST AI RMF, or ISO 42001. Distributed as a TypeScript CLI and Claude Code plugin, it is agent-agnostic (Claude Code, Codex, Cursor, Copilot, Aider, or any OpenAI-compatible runner) and aimed at engineering teams running multiple AI coding agents on a growing codebase who want auditable, operator-controlled automation instead of ad hoc agent usage.
https://github.com/ai-sdlc-framework/ai-sdlc
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.