softwarefactory.build

A directory and guide library for agent-native software factories.

Best of / Open source stacks

Open source stacks

Listings where a substantial client or runtime is publicly licensed. Cloud extras may still be proprietary — read the license field.

Curated by filter, not by score. A listing appears here only if its structured fields match the query. 58 listings.

  1. Agent Development Kit

    Google’s open kit for building Gemini-centered agents.

    Verified

  2. Agno

    Python multi-agent framework (formerly Phidata).

    Verified

  3. Aider

    Git-native CLI agent that commits as it works.

    Verified

  4. Cline

    Open VS Code agent that drives the editor like a human.

    Verified

  5. Cloudflare Agents

    Agents SDK on Durable Objects — this site’s own job runtime.

    Verified

  6. Coder

    Self-hosted workspaces on your infrastructure, Terraform-defined.

    Verified

  7. Context7

    Up-to-date library docs injected into coding agents.

    Verified

  8. Continue

    Open IDE agents, acquired by Cursor, source still public.

    Verified

  9. CrewAI

    Role-playing multi-agent framework with a commercial control plane.

    Verified

  10. Crush

    Charm’s glamorous terminal coding agent.

    Verified

  11. Dagger

    Programmable CI/CD engine agents can call as a tool.

    Verified

  12. Daytona

    Workspaces for agents, with a more persistent posture than E2B.

    Verified

  13. DeepEval

    Pytest-flavored evals for LLM systems.

    Verified

  14. Devbox

    Nix-powered reproducible shells for humans and agents.

    Verified

  15. DSPy

    Stanford’s framework for programming — not prompting — LMs.

    Verified

  16. E2B

    Firecracker microVMs as a sandbox API for AI agents.

    Verified

  17. Fern

    OpenAPI-to-SDKs and docs, an alternative to Stainless.

    Verified

  18. Firecracker

    AWS’s microVM monitor that sandbox vendors wrap.

    Verified

  19. Gemini CLI

    Google’s open-source terminal agent for Gemini models.

    Verified

  20. Giskard

    Open testing and red-teaming for AI applications.

    Verified

  21. Gitpod

    Open-source platform for automated, ready-to-code environments.

    Verified

  22. Goose

    Block’s local-first, open-source agent with recipes.

    Verified

  23. Hatchet

    Open task queue aimed at durable, observable background jobs.

    Verified

  24. Haystack

    deepset’s open framework for pipelines, RAG, and agents.

    Verified

  25. Helicone

    Open LLM gateway with logging, caching, and spend controls.

    Verified

  26. Inngest

    Event-driven durable functions for product and agent jobs.

    Verified

  27. Inspect

    UK AISI’s open framework for evaluating language model agents.

    Verified

  28. Kilo

    Open agent across IDE and CLI, plus a zero-markup model gateway.

    Verified

  29. Langfuse

    Open-source LLM observability you can self-host.

    Verified

  30. LangGraph

    Graph runtime for agents, from the LangChain project.

    Verified

  31. LangWatch

    Observability and evaluation platform for LLM products.

    Verified

  32. Letta

    Stateful agents with memory, from the MemGPT lineage.

    Verified

  33. LlamaIndex

    Data framework for LLM apps that grew workflows and agents.

    Verified

  34. Mastra

    TypeScript agent framework with workflows and evals attached.

    Verified

  35. Microsoft Agent Framework

    Microsoft’s successor surface for AutoGen-style multi-agent apps.

    Verified

  36. n8n

    Open workflow automation that now grows agent nodes.

    Verified

  37. OpenAI Agents SDK

    OpenAI’s official Python/TS SDK for agent loops.

    Verified

  38. OpenCode

    Open terminal coding agent; Kilo CLI is a downstream fork.

    Verified

  39. OpenHands

    Open software-agent runtime with a computer you can watch.

    Verified

  40. Phoenix

    Arize’s open observability and eval notebook for LLM apps.

    Verified

  41. Plandex

    Open terminal agent that plans large diffs in a sandbox.

    Verified

  42. Prefect

    Python workflow orchestrator used to schedule agent jobs.

    Verified

  43. Promptfoo

    Open evals and red-team for LLM apps and agents.

    Verified

  44. Pydantic AI

    Typed Python agents from the Pydantic team.

    Verified

  45. Qodo

    Generation and review agents aimed at test-aware pull requests.

    Verified

  46. Ragas

    Open metrics for RAG and LLM application quality.

    Verified

  47. Roo Code

    Cline fork aimed at modes, automation, and teams.

    Verified

  48. Semgrep

    Fast static analysis you can teach, including AI-assisted rules.

    Verified

  49. smolagents

    Hugging Face’s small, first-class code-agent library.

    Verified

  50. Spec Kit

    GitHub’s toolkit for spec-driven development with coding agents.

    Verified

  51. Steel

    Open-source browser sandbox API for AI agents.

    Verified

  52. SWE-agent

    Princeton’s agent that made SWE-bench a product category.

    Verified

  53. Tabby

    Self-hosted coding assistant you run like an internal service.

    Verified

  54. Temporal

    Durable workflow engine that can sequence factory steps.

    Verified

  55. Trigger.dev

    Background jobs for TypeScript apps, including long agent runs.

    Verified

  56. Vercel AI SDK

    TypeScript SDK for streaming model UIs and tool-calling apps.

    Verified

  57. Warp

    Open terminal, multi-model agents, and factories in early access.

    Verified

  58. Zed

    Open Rust editor with first-class agent panels.

    Verified