10 open-source repos for building the system around Astra
The author lists 10 open-source projects including PydanticAI, LangGraph, Agno, Mem0, E2B, DeepEval and Langfuse, assembling a full Astra setup across building agents, memory, runtime and evaluation.
this is where GPT-6 Astra is getting f...cking illegal 10 open-source GitHub repos I'd use to build the system around the model 01 PydanticAI ▸ https://github.com/pydantic/pydantic-ai → typed agents + structured outputs 02 LangGraph ▸ https://github.com/langchain-ai/langgraph → state + long-running agent workflows BUILD THE AGENTS 03 Agno ▸ https://github.com/agno-agi/agno → agents + teams + workflows 04 smolagents ▸ https://github.com/huggingface/smolagents → agents that execute through code GIVE THEM MEMORY 05 Mem0 ▸ https://github.com/mem0ai/mem0 → persistent agent memory 06 Graphiti ▸ https://github.com/getzep/graphiti → temporal knowledge graphs GIVE THEM A RUNTIME 07 E2B ▸ https://github.com/e2b-dev/E2B → isolated sandboxes for AI-generated code 08 Daytona ▸ https://github.com/daytonaio/daytona → infrastructure for running agent workloads TEST EVERYTHING 09 DeepEval ▸ https://github.com/confident-ai/deepeval → evals for LLM systems 10 Langfuse ▸ https://github.com/langfuse/langfuse → traces + evals + production monitoring the flow: request → agent → memory → tools → runtime → eval → retry → deploy that's the part people underestimate the model is one folder the system around it is the product ⭣
This post quotes another post: x.com/lummox_eth/status/2105607355262009622