Awesome Agent Infrastructure

Awesome Agent Infrastructure [](https://awesome.re) [](http://makeapullrequest.com) [](https://creativecommons.org/publicdomain/zero/1.0/)

A curated list of infrastructure for building reliable LLM agents — frameworks, memory, tool protocols, sandboxes, browsers, observability, and retrieval.

Maintained by Backblaze.

Related Lists

• Awesome ML Data Pipelines
• Awesome Multimodal Data
• Awesome Physical AI
• Awesome Image Generation
• Awesome Video Generation
• Awesome Audio Generation

Contents

• [Agent Frameworks](#agent-frameworks)
• [Memory and State](#memory-and-state)
• [Tool Protocols and Servers](#tool-protocols-and-servers)
• [Execution Sandboxes](#execution-sandboxes)
• [Browser and Computer Use](#browser-and-computer-use)
• [Observability and Evaluation](#observability-and-evaluation)
• [Retrieval and RAG](#retrieval-and-rag)
• [Vector Databases](#vector-databases)
• [Templates and Example Projects](#templates-and-example-projects)

---

Agent Frameworks

> Libraries for building LLM agents — planning, tool use, multi-agent orchestration.

• Microsoft AutoGen – Multi-agent conversation framework from Microsoft Research. AutoGen 0.4 rewrote it around an event-driven runtime. Docs | SDK: Python (pip install autogen-agentchat)
• CrewAI – Role-based multi-agent framework. Agents, tasks, and tools composed into crews with deterministic or planning-based flows. Docs | SDK: Python (pip install crewai)
• Agno – Lightweight Python framework for building multimodal agents and agentic systems. Formerly Phidata. Docs | SDK: Python (pip install agno)
• LangGraph – Graph-based agent runtime from the LangChain team. Durable execution, human-in-the-loop, and multi-actor patterns. Docs | SDK: Python (pip install langgraph), JS (npm install @langchain/langgraph)
• HuggingFace smolagents – Minimal "code agent" library — agents write Python to solve tasks. ~1k LoC core; easy to audit and extend. Docs | SDK: Python (pip install smolagents)
• Mastra – TypeScript-first agent framework with workflows, RAG, and evals. From the creators of Gatsby. Docs | SDK: TypeScript (npm install @mastra/core)
• OpenAI Agents SDK – Official OpenAI agent framework. Handoffs, guardrails, built-in tracing, and Responses-API-native execution. Docs | SDK: Python (pip install openai-agents)
• Pydantic AI – Agent framework from the Pydantic team. Type-safe tool calling, structured outputs, dependency injection. Docs | SDK: Python (pip install pydantic-ai)
• AG2 – Community-maintained fork of AutoGen 0.2. Multi-agent conversation framework with swarms, group chats, and nested chat patterns. Docs | SDK: Python (pip install ag2)
• AgentScope – Python agent framework with an event-driven runtime, human-in-the-loop, sandboxed tool execution, and Agent-as-a-Service REST deployment. v2.0 released May 2026. Docs | SDK: Python (pip install agentscope)
• DeerFlow – ByteDance's open-source super-agent harness built on LangGraph. Orchestrates sub-agents, memory, sandboxes, and skills for long-horizon tasks. Docs
• Flowise – Open-source visual builder for LLM agents and workflows. Drag-and-drop Agentflow canvas plus REST API, JS/Python SDK, and CLI for programmatic integration into production applications. Docs | SDK: TypeScript (npm install -g flowise)
• Google ADK – Google's open-source agent development kit. Build, evaluate, and deploy multi-agent systems; multi-language with Gemini-optimized but model-agnostic. Docs | SDK: Python (pip install google-adk), TypeScript (npm install @google/adk)
• Langflow – Low-code builder for AI agents and RAG applications. Visual canvas with Python escape hatches, deploys flows as REST APIs or MCP servers; 40+ model and vector-store integrations. Docs | SDK: Python (pip install langflow)
• Langroid – Lightweight Python multi-agent framework from CMU/UW-Madison. Task-delegation via message passing; no LangChain dependency. Docs | SDK: Python (pip install langroid)
• MetaGPT – Multi-agent framework that assigns software-company roles (PM, architect, engineer) to LLMs. Input a requirement, get PRD, design, code, and tests. Docs | SDK: Python (pip install metagpt)
• Microsoft Agent Framework – Microsoft's production-ready open-source agent SDK and runtime for Python and .NET. Unifies AutoGen orchestration and Semantic Kernel foundations. Docs | SDK: Python (pip install agent-framework), .NET (dotnet add package Microsoft.Agents.AI)
• open-multi-agent – TypeScript multi-agent orchestration with automatic goal-to-DAG decomposition, parallel task execution, MCP integration, and live tracing. Three runtime dependencies; 10+ LLM providers supported. SDK: TypeScript (npm install @jackchenme/open-multi-agent)
• OpenAI Agents SDK (TypeScript) – Official OpenAI agent framework for TypeScript and JavaScript. Agents, handoffs, guardrails, voice via Realtime API, and built-in tracing. Docs | SDK: TypeScript (npm install @openai/agents)
• OpenSRE – Open-source toolkit for building AI SRE agents. Connects to 60+ observability, cloud, and incident-management tools; auto-fetches alert context, correlates logs/metrics, and generates root-cause reports.
• Semantic Kernel – Microsoft's open-source SDK for building LLM agents and multi-agent systems. Model-agnostic; plugins, planners, and process orchestration across Python, C#, and Java. Docs | SDK: Python (pip install semantic-kernel), C# (dotnet add package Microsoft.SemanticKernel), Java (Maven: com.microsoft.semantic-kernel)
• Strands Agents – AWS-backed open-source agent SDK. Define tools as functions; the model-driven loop handles planning and execution with no workflow graphs required. Docs | SDK: Python (pip install strands-agents), TypeScript (npm install @strands-agents/sdk)
• VoltAgent – TypeScript agent framework with memory adapters, RAG, tool registry, multi-agent supervisor coordination, voice support, and built-in evals. Docs | SDK: TypeScript (npm create voltagent-app@latest)

Memory and State

> Long-term memory, session state, and knowledge-retention layers for agents.

• Mem0 – Memory layer for AI agents. Personalization through user/agent/session memories with semantic recall. Docs | SDK: Python (pip install mem0ai), Node (npm install mem0ai)
• Letta – Open-source agent server focused on long-term memory. Successor to MemGPT; agents are first-class stateful services. Docs | SDK: Python (pip install letta-client)
• Zep – Memory and context platform for LLM apps. Knowledge-graph-backed user memory with temporal reasoning. Docs
• Cognee – Knowledge engine for agent memory. ECL pipeline ingests any data into a hybrid vector + knowledge graph for structured, traceable recall. Docs | SDK: Python (pip install cognee)
• Graphiti – Open-source temporal context graph engine. Tracks how facts change over time with full provenance; hybrid semantic + keyword + graph retrieval. Docs | SDK: Python (pip install graphiti-core)
• Hindsight – Open-source agent memory system using biomimetic data structures. Organises memories into world facts, experiences, and mental models; TEMPR retrieval combines semantic, keyword, graph, and temporal search. Docs | SDK: Python (pip install hindsight-client), TypeScript (npm install @vectorize-io/hindsight-client)
• Honcho – Memory infrastructure for stateful agents. Stores messages to per-peer sessions, runs background reasoning to build user representations, and returns curated context via a fast query API. Docs | SDK: Python (uv add honcho-ai)
• Puppyone – File system for agents. Connect, govern, version, and share context across agent workflows. Docs
• Redis Agent Memory Server – Memory layer for AI agents backed by Redis. Two-tier working + long-term memory, semantic/keyword/hybrid search, REST and MCP interfaces, and multi-LLM provider support. Docs | SDK: Python (pip install agent-memory-client)
• ReMe – Memory management kit for AI agents. Conversation compaction, long-term file-based and vector memory, semantic search; compresses context by up to 99.5% while retaining critical facts. Docs | SDK: Python (pip install reme)
• Supermemory – Memory and context API for AI agents. Ingests documents and conversations, extracts facts, builds user profiles, and returns relevant context via hybrid semantic search; SDK and REST interfaces. Docs | SDK: TypeScript (npm install @supermemory/sdk), Python

Tool Protocols and Servers

> Standardised interfaces for exposing tools and data sources to agents (MCP and friends).

• MCP Reference Servers – Reference MCP server implementations for filesystem, Git, GitHub, SQL, Slack, and more.
• MCP Python SDK – Official Python SDK for building and consuming MCP servers and clients. SDK: Python (pip install mcp)
• MCP TypeScript SDK – Official TypeScript SDK for MCP servers and clients. SDK: TypeScript (npm install @modelcontextprotocol/sdk)
• Anthropic Model Context Protocol – Open protocol for connecting AI applications to tools and data sources. Spec, reference servers, and official SDKs. Docs
• Agent2Agent Protocol (A2A) – Open protocol for communication and interoperability between AI agents. JSON-RPC 2.0 over HTTP with SDKs for Python, Go, JS, Java, and .NET. Docs
• AWS MCP Servers – Suite of 53 open-source MCP servers for AWS services — CloudFormation, Bedrock, DynamoDB, EKS, S3, and more. Docs
• Composio – Tool-integration SDK for AI agents. 1000+ pre-built tool connectors (GitHub, Slack, Jira, etc.) with managed auth and sandboxed execution. Docs | SDK: Python (pip install composio), TypeScript (npm install @composio/core)
• Headroom – Context compression layer for AI agents. Compresses tool outputs, logs, RAG chunks, and files 60-95% before they reach the LLM; runs as a library, proxy, or MCP server with reversible compression. SDK: Python (pip install headroom)
• IBM ContextForge – Open-source MCP/A2A/REST gateway and registry. Federates MCP servers, A2A agents, and REST/gRPC APIs behind a single governed endpoint with auth, rate limiting, and OpenTelemetry tracing. Docs | SDK: Python (pip install mcp-contextforge-gateway)
• MCP Inspector – Interactive visual tool for testing and debugging MCP servers. Supports STDIO, SSE, and Streamable HTTP transports. SDK: TypeScript (npx @modelcontextprotocol/inspector)
• MCPX – Open-source MCP gateway and aggregator. Consolidates multiple MCP servers behind a single governed entry point with rate limiting and traffic policies. Docs
• n8n-mcp – MCP server exposing n8n's 1,650+ workflow nodes to AI agents. Provides node docs, schema properties, operations, and workflow validation for agents building n8n automations. SDK: TypeScript (npx n8n-mcp)

Execution Sandboxes

> Secure environments for running agent-generated code, shell commands, and browser sessions.

• Daytona – Open-source dev-environment manager; Daytona Sandboxes expose a sandbox API for agents and CI pipelines. Docs
• E2B – Secure cloud sandboxes for running AI-generated code. Firecracker microVMs, sub-second startup, per-session isolation. Docs | SDK: Python (pip install e2b), JS (npm install @e2b/code-interpreter)
• Microsoft Agent Governance Toolkit – Runtime policy enforcement for autonomous agents. Zero-trust identity, execution sandboxing, sub-millisecond policy checks; covers all 10 OWASP Agentic Top 10 risks. SDK: Python (pip install agent-governance-toolkit), TypeScript (npm install @microsoft/agentmesh-sdk)
• Modal Sandboxes – Serverless sandbox primitive inside Modal. Arbitrary container execution, ephemeral filesystems, strict network policies.
• OpenShell – NVIDIA's open-source sandbox runtime for autonomous agents. Declarative YAML policies govern file access, network activity, and data exfiltration; supports Claude, Codex, Copilot, and OpenCode. SDK: Python (uv tool install openshell)
• Riza – Secure code-execution API for LLM tool calls. Python, JS, PHP, Ruby; strict WASM-based isolation. Docs

Browser and Computer Use

> Platforms and SDKs that let agents drive web browsers and full desktops.

• **[browser

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: backblaze-labs
• Source: backblaze-labs/awesome-agent-infrastructure
• License: CC0-1.0
• Homepage: https://blze.ai/storage

Install and usage instructions live in the source repository linked above.