38.8K stars but only 1.45M PyPI/month — DL/star ratio of 37 is the 3rd most inflated in the category. $5.4M funding (PitchBook). Full-stack offering: agents + teams + workflows + AgentOS control plane. Performance claims (10,000x faster instantiation, 50x less memory) are single-source and unverified. All HN submissions appear to be from the same user (likely founder).
Where it wins
38.8K GitHub stars — top 3 by stars in category
Full-stack offering: agents, teams, workflows, AgentOS control plane
$5.4M funding (PitchBook)
Active development — last push 2026-03-19
Where to be skeptical
DL/star ratio of 37 — 3rd most inflated in category
All HN submissions appear from same user (likely founder) — self-promotional pattern
Performance claims (10,000x faster, 50x less memory) are single-source, unverified
No independently confirmed enterprise customers
Editorial verdict
Include with caveats. High star count but inflated DL/star ratio and self-promotional HN pattern. No independently confirmed enterprise customers. Full-stack offering is ambitious but evidence is thin. Re-evaluate upward if independent enterprise evidence surfaces.
Source
Related
Claude Code
98Anthropic's official agentic coding CLI. v2.1.81 (Mar 20) shipped `--bare`, smarter worktree resume, and improved MCP OAuth while the repo crossed 82,204 stars and logged ~14 commits/week across 10+ maintainers. Terminal-native, tool-use-driven, with deep file system + shell access, #1 SWE-bench Pro standardized (45.89%), ~4% of GitHub public commits (SemiAnalysis), $2.5B annualized revenue. 8M+ npm weekly downloads. Opus 4.6 with 1M context.
LangGraph
95#1 Python agent framework by production evidence — 40.2M PyPI downloads/month, Fortune 500 deployments (LinkedIn, Uber, Replit, Elastic, Klarna, Cloudflare, Coinbase), ~400 LangGraph Platform companies, LangSmith rated best-in-class observability. Stable v1.x API, model-agnostic, MCP support.
Pydantic AI
95#3 Python agent framework by downloads — 15.6M PyPI/month. Built by the Pydantic team. Runtime type enforcement is a genuine differentiator no other framework offers. V1 shipped with Temporal integration for durable execution and Logfire observability. Emerging pattern: 'Pydantic AI for agent logic, LangGraph for orchestration' (ZenML).
AutoGen (Microsoft)
95⚠️ MAINTENANCE MODE — Microsoft officially confirmed bug fixes and security patches only, no new features (VentureBeat 2026-02-19). 55.9K stars but only 1.57M PyPI/month — DL/star ratio of 28, the most inflated among active frameworks. Being replaced by Microsoft Agent Framework (AutoGen + Semantic Kernel merge, GA targeted ~Q2 2026). Teams on AutoGen should plan migration.
Public evidence
DL/star ratio of 37 vs LangGraph's 1,516. Star count significantly outpaces actual deployment. Community interest outpaces production adoption.
Modest funding relative to category peers. Enough runway to iterate but not enterprise-scale backing.
Raw GitHub source
Constrained peek so you can sanity-check the source material without leaving the site.
Agno is a framework and runtime for agent platforms. Build agents, run them as a service, manage your platform using a web UI.
Agno allows you to own your agent stack. Maintain control of your data, memory, and security posture (JWT-based RBAC), and turn your agent platform into a learning loop with simulations and usage data.
<img width="3192" height="2038" alt="demo-os" src="https://github.com/user-attachments/assets/6d21e6bc-111f-4b81-ba29-6550fead89b2" />Hand this prompt to your coding agent (Claude Code, Cursor, Codex):
Help me set up my agent platform.
Clone https://github.com/agno-agi/agentos-railway into a folder called
agent-platform, cd in, read the README, and follow the get started guide.
Your coding agent will set up your agent platform and run it locally using Docker, giving you a REST API for serving your agents, a Postgres database for storing your data and traces, an MCP server, and a control plane.
Deploying somewhere else? Use the same prompt but point it to a different repo. The starter templates are identical except for the deploy scripts: swap agentos-railway for agentos-docker, agentos-aws, agentos-gcp, agentos-azure, agentos-fly, agentos-render, agentos-modal, or agentos-helm.
Two options:
https://docs.agno.com/llms-full.txt. Also works in VSCode, Windsurf, and similar tools.Read the full guide here.
See the contributing guide.
Agno is distributed under the Apache-2.0 license.
Agno sends a telemetry event per agent run so we know which model providers to prioritize. Prompts, messages, and outputs are never sent. Disable by setting AGNO_TELEMETRY=false.