Tag
Python tools
8 reviewed tools: 8 free or open source.
Order: free and open source first, then hosted products with a real free tier, then paid-led; catalog order inside each group, with quiet or archived repos last. Not a score, and no tool pays for its place.
8 tools
- Pydantic AITyped Python agent loop with a snap-on Coder harness
Free / OSS · OSS/MIT · 20.7k GitHub stars
VerdictThe typed Python agent SDK. Not the validator. ACP is still experimental.
CatchACP (Agent Client Protocol, for editors like Zed) is experimental: it lives under pydantic_ai_harness.experimental.acp, may change or be removed in any release without a deprecation period, and importing it emits HarnessExperimentalWarning. Coder is a capability you assemble, not a turnkey SWE agent like OpenHands. Logfire is the convenient observability path; OpenTelemetry works with any backend. Do not confuse this gem with Pydantic validation.
- AgnoApache-2.0 Python agent framework + AgentOS runtime (ex-Phidata)
Free / OSS · Apache-2.0 · 42.8k GitHub stars
VerdictApache-2.0 Python agents + AgentOS. Ship on Agno, not Phidata nostalgia.
CatchVs LangGraph (graphs), CrewAI (roles), Mastra (TypeScript): Agno is Python performance + AgentOS productization, not a coding CLI like Claude Code/OpenCode. Phidata docs/imports are dead—use Agno. Control Plane and hosted conveniences are optional; day-one is OSS SDK+runtime you operate.
- AG2Apache-2.0 open-source AgentOS; AutoGen community continuation
Free / OSS · Apache-2.0 · 5k GitHub stars
VerdictApache-2.0 AutoGen community AgentOS. Use AG2 for OSS; Microsoft Agent Framework if you want the MS successor.
CatchVs microsoft/autogen (maintenance; MS points new work to Microsoft Agent Framework) and LangGraph/CrewAI: AG2 is the community AutoGen fork, not Microsoft’s enterprise successor. AG2 v1 is not a drop-in from Classic — pin ag2-classic / import autogen if you need the old surface. One primary entry; do not twin with dead AutoGen marketing.
- DSPyMIT program LMs with signatures and optimizers (Stanford NLP)
Free / OSS · OSS/MIT · 38.7k GitHub stars
VerdictMIT LM programming framework. Optimize modules; do not confuse it with MCP runtime glue.
CatchVs LangChain/LangGraph (orchestration graphs) and Promptfoo (YAML eval/red-team): DSPy is program-and-optimize LMs, not an MCP-first runtime and not a hosted eval SaaS. Optimizer runs cost tokens/compute; you still bring models and data. Not a drop-in coding agent.
- CAMELApache-2.0 multi-agent framework — scaling laws of agents
Free / OSS · Apache-2.0 · 17.9k GitHub stars
VerdictApache-2.0 multi-agent framework. Scale agent societies; Eigent is a different product.
CatchVs CrewAI / AG2 (product multi-agent orchestration) and OpenHands / SWE-agent (coding agents): CAMEL is multi-agent research/framework breadth, not a turnkey SWE seat. Eigent is a separate commercial cousin — do not treat CAMEL OSS as Eigent cloud. You own model spend and orchestration choices.
- FletApache-2.0 cross-platform GUI from Python
Free / OSS · Apache-2.0 · 17.4k GitHub stars
VerdictApache-2.0 Python UI framework. Reach for graphical cross-platform apps, not a Textual-style TUI; verify the release surface you pin.
CatchVs Textual: Flet targets cross-platform graphical interfaces, while Textual is a terminal UI. Cross-platform does not erase platform packaging, runtime, or native-widget trade-offs; verify the project’s current release/support matrix before pinning a version. No unreleased 1.0 claim here.
- Monty (Pydantic)MIT in-process Rust Python sandbox — OSS Monty only
Free / OSS · OSS/MIT · 8.7k GitHub stars
VerdictMIT in-process Python sandbox when agents need Pydantic Monty OSS — not E2B/AIO/CubeSandbox cloud or KVM seats; ignore the ★ spike.
Catch★8499 in about 41 weeks (~207 a week): judge it on the sandbox shape, not the star count. Vs E2B / AIO Sandbox / CubeSandbox: those are hosted Firecracker seats, broader sandbox/browser/MCP runtimes, or self-hosted RustVMM/KVM density — Monty’s catch is in-process Rust Python sandbox from Pydantic, not a sandbox SaaS seat. Do not confuse OSS Monty packages with Full Monty commercial; pin the MIT crates/npm/PyPI names.
- build123dApache-2.0 Python CAD-as-code on Open Cascade — the library under text-to-cad
Free / OSS · Apache-2.0 · 3.5k GitHub stars
VerdictApache-2.0 Python CAD library when you need code-first solids — free via pip; for the agent seat see text-to-cad.
CatchRaw modeling library: no agent harness, no MCP, no viewer — pair with text-to-cad when an agent should drive CAD. Heavy Open Cascade / OCP install (native wheels, first install is large and platform-sensitive). Vs FreeCAD/CadQuery: CadQuery is the older Python OCCT layer; build123d is the newer ergonomic API many agent tools standardize on. Geometric correctness still needs a human tolerance pass before you cut metal.
FAQ
- What is the top free pick among Python tools?
- Pydantic AI leads the Stack Gems list for Python tools. Verdict: The typed Python agent SDK. Not the validator. ACP is still experimental.
- How many Python tools does Stack Gems review?
- 8: 8 free or open source. Each review has a verdict and an honest Catch; no tool pays for its spot.
- Which Python tools can I self-host for free?
- Pydantic AI, Agno, AG2, DSPy, CAMEL, Flet, Monty (Pydantic) and build123d.
- Which Python tools have the most GitHub stars?
- Agno (42.8k), DSPy (38.7k), Pydantic AI (20.7k), per GitHub on 2026-10-19. Stars measure attention, not fit; read the Catch.
- What is the catch with Pydantic AI?
- ACP (Agent Client Protocol, for editors like Zed) is experimental: it lives under pydantic_ai_harness.experimental.acp, may change or be removed in any release without a deprecation period, and importing it emits HarnessExperimentalWarning.