langchain vs agno
Two of the top projects in Agent frameworks and SDKs, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
langchain
Python framework for building LLM agents and apps from interoperable components
agno
Python SDK and runtime for building and serving agents behind a REST API
Verdict
langchain ranks higher, 88 to 69. Of the 4 score parts we measure for both, langchain leads on 2, agno on 1 and 1 is even.
- Adoptionlangchain leads by 66 points, 97 to 31: a wide gap.
- FreshnessEven at 100.
- Maintenancelangchain leads by 8 points, 85 to 77.
- Agent-readyagno leads by 40 points, 70 to 30: a wide gap.
Pick langchain if you are
Python developers building LLM agents and applications in code
- Common interface across model providers, embeddings and vector stores
- Large integrations library covering tools, retrievers and vector stores
Pick agno if you are
Python developers building self-hosted multi-user agent services
- Runtime ships a REST API with 50+ endpoints, SSE and websockets
- JWT-based RBAC and multi-tenant isolation included
| What we compare | langchain | agno |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 97, widely used | 31, known |
| Freshness | 100, active | 100, active |
| Maintenance | 85, healthy | 77, fair |
| Easy to run | Not scored for this kind | Not scored for this kind |
| Agent-ready | 30, minimal | 70, partly |
| Facts from GitHub and the README | ||
| Stars | 147.8k | 42.7k |
| License | MIT (permissive) | Apache-2.0 (permissive) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Oct 2026 | Oct 2026 |
| Language | Python | Python |
| Docker | No | No |
| GPU | Not stated | Not stated |
| arm64 or Apple Silicon | Not stated | Not stated |
langchain
LangChain is a Python library that gives a standard interface to chat models, embeddings, vector stores and tools, so providers can be swapped with little code change. Models load through init_chat_model with a provider:model string. For lower-level agent orchestration it points to LangGraph, and for tracing and evals to LangSmith.
Who it is for: Python developers building LLM agents and applications in code
Strengths
- Common interface across model providers, embeddings and vector stores
- Large integrations library covering tools, retrievers and vector stores
- Companions: LangGraph for orchestration, Deep Agents for planning and subagents
- MIT license; JS/TS counterpart available as LangChain.js
Weaknesses
- Observability, evals and managed deployment sit in LangSmith, a separate product
- Controllable stateful agent workflows need LangGraph, not core LangChain
- README gives no hardware requirements or list of supported providers
- Abstraction layer is another API to learn on top of provider SDKs
- Needs Model provider API or other model backend
- Models: OpenAI (README example), Other providers via integrations
agno
Agno is a Python framework for defining agents, plus the AgentOS runtime that serves them through a REST API with 50+ endpoints, SSE and websockets. Sessions, memory, knowledge and traces are stored in your own database, and a web UI manages the running platform. It includes JWT-based RBAC, human approval steps, cron scheduling, and interfaces for Slack, Telegram, WhatsApp, Discord, AG-UI and A2A.
Who it is for: Python developers building self-hosted multi-user agent services
Strengths
- Runtime ships a REST API with 50+ endpoints, SSE and websockets
- JWT-based RBAC and multi-tenant isolation included
- 100+ prebuilt toolkits plus OpenTelemetry tracing and audit logs
- Starter templates for Docker, AWS, GCP, Azure, Fly, Render, Modal and Helm
Weaknesses
- Sends a telemetry event per agent run unless AGNO_TELEMETRY=false is set
- README gives no RAM, GPU or port requirements
- Starter templates live in separate repos, not in this one
- Management UI hosting and licensing terms are not described in the README
- Needs Postgres, Docker
- Models: unknown
More in Agent frameworks and SDKs
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.