11–20 of 93 posts
Never again committing to any "framework", especially when something like Claude Code can write one for you from scratch exactly for what you want.
We have code on demand. Shallow libraries and frameworks are dead.
all of these frameworks will go away once the model gets really smart. it will just be tool search, tools, and the model in the short run, ive found the open ai agents one to be the best
If you have a narrow task that doesn't need full context, then agent delegation (putting an agent or inference behind a simple tool call) can be effective. A good example is to front your RAG with a search() tool with a simple "find the answer" agent that deals with the context and can run multiple searches if needed.
I think the PydanticAI framework has the right approach of encouraging Agent Delegation & sequential workflow first and trying to steer you away graphs[0]
You should also try to make context query the first class primitive.
Context query parameter can be natural language instruction how to compact current context passed to subagent.
When invoking you can use values like "empty" (nothing, start fresh), "summary" (summarizes), "relevant information from web designer PoV" (specific one, extract what's relevant), "bullet points about X" etc.
This way LLM can decide what's relevant, express it tersly and compaction itself will not clutter current context – it'll be handled by compaction subagent in isolation and discarded on completion.
What makes it first class is the fact that it has to be built in tool that has access to context (client itself), ie. it can't be implemented by isolated MCP because you want to avoid rendering context as input parameter during tool call, you just want short query.
Ie. you could add something like:
handover(prompt, context_query, depends_on: { conversation_id_1: "result", conversation_id_2: "just result number" }) -> conversation_id"
I’ve found both the open source TodoWrite and building your own TodoWrite with a backing store surprisingly effective for Planning and avoiding developer defined roles and developer defined plans/workflows that the author calls in the blog for AI-SRE usecases. It also stops the agent from looping indefinitely.
Cord is a clever model and protocol for tree-like dependencies using the Spawn and Fork model for clean context and prior context respectively.
I've been playing with a closely related idea of treating the context as a graph. Inspired by the KGoT paper - https://arxiv.org/abs/2504.02670
I call this "live context" because it's the living brain of my agents
all of these frameworks will go away once the model gets really smart. it will just be tool search, tools, and the model in the short run, ive found the open ai agents one to be the best
This approach seems interesting, but in my experience, a single "agent" with proper context management is better than a complicated agent graph. Dealing with hand-off (+ hand back) and multiple levels of conversations just leaves too much room for critical information to get siloed. If you have a narrow task that doesn't need full context, then agent delegation (putting an agent or inference behind a simple tool call…
Earlier quoted context omitted.
This approach seems interesting, but in my experience, a single "agent" with proper context management is better than a complicated agent graph. Dealing with hand-off (+ hand back) and multiple levels of conversations just leaves too much room for critical information to get siloed. If you have a narrow task that doesn't need full context, then agent delegation (putting an agent or inference behind a simple tool call…
This isnt true for big code bases. Subagents or orchestration become vital for context handholding
all of these frameworks will go away once the model gets really smart. it will just be tool search, tools, and the model in the short run, ive found the open ai agents one to be the best