Pickaxe
AI
agent framework library
SHOW HN2025
How HN took it
8 positive, 9 neutral or asking, 0 mixed, 5 critical, out of 22 comments about the project. Thread score +0.09.
Idea: 6 for, 0 againstPerformance: 0 for, 2 againstDesign: 0 for, 1 againstDocs: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Durable execution and checkpointing are needed for agents; the waitFor pattern is well designed
From 2 comments
Cool work, durable execution and resumability are hugely underrated problems in the agent space, especially once you move beyond toy demos. Love the checkpointing + waitFor…
necatiozmen on HNOh this is really cool! I was building out a bit of this with Restate this past week, but this seems really well put together :) will give it a try!
randomcatuser on HN
Helps people learn what agents are
From 1 comment
What I really like about it, is that this kind of project helps people learn what an agent is.
almosthere on HN
Objections
Relies on Hatchet, which commenters say is not stable or performant enough
From 2 comments
As a long time Hatchet user, I understand why you’ve created this library, but it also disappoints me a little bit. I wish more engineering time was spent on making the core…
zegl on HNHatchet is not stable.
revskill on HN
Lack of documentation on what the code looks like without the library
From 1 comment
It would be great to have a section in the README about how the code looks without using the library, contrasting it with the example you already have. I would need a significant…
gerardosuarez on HN
Tying the API to the Vercel AI SDK risks lagging provider features
From 1 comment
I think providing examples and sample code is better than tying your API to AI sdk. Due to how fast AI providers are iterating on their APIs, many features arrive weeks or months…
cmdtab on HN
Name clashes with pickaxe.co
From 1 comment
The library name is confusing given https://pickaxe.co/, a nicely done low code platform for building/monetizing chatbots and agents that's been around for 2.5 years or so. (No…
j_rosenthal on HN
Requests
Agent-to-client streaming and resumable message streams
From 2 comments
This is great, and I keep my fingers crossed for Hatchet! One use case I imagine is key here is background/async agents, so OpenAI Codex/Jules style, so that's great if I can…
movedx01 on HNPretty much was my first question if there was support for streaming events. Any way we could be beta tester? ༼ つ ◕_◕ ༽つ
cmdtab on HN
Ability to choose different models and prompts per task
From 1 comment
I see the API is rarely mentioning exact message structure (system prompt, assistant/user history, etc) or the choice of model (other than defaultLanguageModel). And it's not…
blixt on HN
Lower-level API so the user can handle LLM calls and streaming
From 1 comment
I think providing examples and sample code is better than tying your API to AI sdk. Due to how fast AI providers are iterating on their APIs, many features arrive weeks or months…
cmdtab on HN
Questions
How does it compare to Mastra?
From 1 comment
Love to see more frameworks like this in the Typescript eco-system! How does this compare to Mastra: https://mastra.ai/
awaseem on HN
How does it compare to Inngest's agent-kit?
From 1 comment
How does this compare to agent-kit by inngest?
muratsu on HN
How to handle chat history and multiple tools in a chat assistant?
From 1 comment
If I understand it correctly, tools and agents run() method works in a similar way to react hooks, correct? Depending on execution order, tool is either called or a cached value…
jskalc92 on HN
Alternatives named
Mastra
From 1 comment
Love to see more frameworks like this in the Typescript eco-system! How does this compare to Mastra: https://mastra.ai/
awaseem on HN
Inngest agent-kit
From 1 comment
How does this compare to agent-kit by inngest?
muratsu on HN
Restate
From 1 comment
Oh this is really cool! I was building out a bit of this with Restate this past week, but this seems really well put together :) will give it a try!
randomcatuser on HN
VoltAgent
From 1 comment
Cool work, durable execution and resumability are hugely underrated problems in the agent space, especially once you move beyond toy demos. Love the checkpointing + waitFor…
necatiozmen on HN