Libraries and SDKs
Lightweight runtimes, tool loops, and provider-agnostic harness primitives.
| # | Project | Stars | Tier | OSS | Description |
|---|---|---|---|---|---|
| 1 | Daytona sandbox | 71.7k | slightly complex | ✅ | Elastic dev environments for AI-generated code: workspaces, Git, previews—infra harness between "the model wrote a patch" and "it ran in a real machine." ⚠️ Public repo unmaintained since June 2026: core development moved to a private codebase (final open release v0.190.0, AGPL-3.0). |
| 2 | LiteLLM provider-agnosticpython | 59.2k | mostly simple | ✅ | One interface to 100+ LLMs; routing, caching, budgets. Not an agent framework—the pipe every agent framework uses. |
| 3 | Composio sandboxtool-discoverypythontypescript | 30.3k | complex | ✅ | 1,000+ toolkits with auth, tool search, and a sandboxed workbench—drop-in tool layer so agents stop reinventing OAuth + integrations. Python and TypeScript. |
| 4 | deepagents multi-agentsandboxpythontypescript | 29.6k | slightly complex | ✅ | LangChain's Python+TypeScript agent harness on top of LangGraph: planning tool, virtual filesystem, shell sandbox, sub-agent spawning—the "Claude Code-style" harness as a reusable library. |
| 5 | smolagents sandboxpython | 29.4k | mostly simple | ✅ | Code-as-action agents: model outputs Python executed in sandbox (E2B, Modal, etc.); ~1k LOC core. |
| 6 | vercel/ai provider-agnostictypescript | 26.9k | slightly complex | ✅ | React and Node SDK for streaming, tool calls, and agent-style UIs; provider-agnostic. |
| 7 | pydantic-ai mcptypedprovider-agnosticpython | 20.1k | slightly complex | ✅ | Type-safe Python agents with Pydantic I/O; multi-provider, MCP, Logfire observability, and human-in-the-loop. |
| 8 | E2B sandboxpython | 13.9k | slightly complex | ✅ | Firecracker sandboxes for executing agent-generated code; the hosted isolation layer many tool-calling demos use instead of running arbitrary LLM output on your laptop. |
| 9 | Steel memorybrowserlocal | 7.7k | slightly complex | ✅ | Open-source browser API for agents: cloud or self-hosted Chrome sessions with stealth, residential proxies, CAPTCHA solving, and persistent profiles. The only open-source core in the hosted browser-infrastructure lane (Browserbase and Hyperbrowser are closed). |
| 10 | strands-agents mcpmulti-agenttypedpython | 7.4k | mostly simple | ✅ | Model-driven Python SDK; decorators for tools, native MCP, multi-agent; "minimal code" without sacrificing provider choice. |
| 11 | Cloudflare Agents memorytypescript | 5.6k | slightly complex | ✅ | Persistent, stateful agents on Durable Objects: state, websockets, scheduling, and AI chat baked in. The serverless answer to "where does the agent live?" |
| 12 | Agent Sandbox memorysandboxlocal | 4k | slightly complex | ✅ | Kubernetes-native sandbox primitive for agent runtimes: a Sandbox resource plus warm pools and claims for fast-start, isolated, stateful workloads. The self-hosted answer to hosted sandbox APIs, from the Kubernetes SIGs org. |
| 13 | openai-agents-js multi-agentvoicetypescript | 3.8k | slightly complex | ✅ | Official OpenAI Agents SDK for Node/TS: handoffs, guardrails, voice; the JS counterpart to openai-agents-python. |
| 14 | open-harness mcpmulti-agenttypescript | 612 | slightly complex | ✅ | TypeScript Agent class on Vercel AI SDK; streaming events, filesystem/bash tools, MCP, and subagent delegation. |
| 15 | Community-curated agent lists | 15 | super simple | ❓ | Broader directories: e.g. [brandonhimpfen/awesome-ai-agents](https://github.com/brandonhimpfen/awesome-ai-agents), [axioma-ai-labs/awesome-ai-agent-frameworks](https://github.com/axioma-ai-labs/awesome-ai-agent-frameworks), [mb-mal/awesome-ai-agents-frameworks](https://github.com/mb-mal/awesome-ai-agents-frameworks)—differ by scope and update cadence. |