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
OpenSwarm is an autonomous AI agent orchestrator designed to automate software development tasks. It deploys multiple AI agents as 'code workers' to tackle issues from Linear, manage pair programming pipelines (Worker/Reviewer), report progress to Discord, and build long-term cognitive memory using LanceDB. The system supports various LLM providers, including Claude Code, OpenAI GPT, OpenRouter for accessing a wide range of models, and local open-source models like Ollama, LMStudio, and llama.cpp, with a focus on cost-aware routing. A key feature is the agentic harness's ability to solve SWE-bench Lite instances, demonstrating its capability to resolve complex issues, especially in a hybrid model where frontier models diagnose and lightweight models implement and verify. OpenSwarm enables agents to learn continuously from their task outcomes, storing per-repository knowledge for future prompts. It provides a TUI chat interface for interaction, along with CLI commands for starting daemons, running single tasks, and executing pipelines. The daemon setup allows for full autonomous operation, integrating with Discord for control and Linear for issue management. Configuration is flexible, accommodating different LLM adapters, defining agent roles (worker, reviewer, tester, documenter, auditor), and setting up scheduling for autonomous operations. It includes features like a Code Registry for scanning repositories, identifying patterns, and assessing risks, and supports deployment as a macOS launchd service, manual npm execution, or via Docker Compose. The platform emphasizes an agentic loop for tool use (read/search/edit/bash) with verification guards, and cost-efficient scaling by leveraging various models.
https://github.com/unohee/OpenSwarm
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.
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...
SuperAGI is an open-source framework designed for building, managing, and running autonomous AI agents, offering tools for deployment, capability extension, and performance monitoring.
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-...
Astron Agent is an enterprise-grade platform for building, orchestrating, and deploying AI agent applications with integrated RPA, model management, and high-availability features.
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.
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 is an open-source platform for building, orchestrating, and self-hosting agent-based AI workflows with persistent memory and tool integration.