Just downloaded the notes, then told Claude to organize and remove duplicate or index mds (Notion keeps a lot of random indexes) and clean up and within 30mins i had a very clean and usable (and agent accessible) md vault. I can open it in Obsidian or other md file viewer (as well as my own code editor). I opted for obsidian.

Setup was super straight-forward. I do miss the visual editor in Notion (obsidian editor is not as smooth, and i find myself just writing the files in text instead of using their visual mode).

for sync, i use icloud, and it syncs between the iphone and the mac app flawlessly, didn't have any issue with corruptions (yet). I use the phone app as mostly an intake, and the desktop app for mostly visualizations. I also tinkered with adding git to track history (has to put the .git folder outside the repo with --separate-git-dir).

Obsidian has a terminal support (which i suppose folks can use to run agents in there) although i found it easier (habbit perhaps) to run my agents separately. They provide massive unlock as their turn my knowledge to an actual insight and can connect things that i didn't think it was possible before.

Overall, 75% happy. From first principle, file is as simple as it gets and i think this is good enough personal knowledge management. I do miss sharing capabilities as well as multi-user in Notion, so i don't think this is useful for 2player/team/corp.

Surprisingly it never gained the adoption it deserved.

Source: i run pretty much all of these agents (codex, cc, droid, opencode, amp, etc) side-by-side in agentastic.dev and opencode had basically 0 win-rate over other agents.

[1]https://github.com/facebookresearch/cwm [2]https://huggingface.co/facebook/cwm

Comments URL: https://news.ycombinator.com/item?id=46772138

Points: 2

# Comments: 0

i think the distribution channel is the only defensive moat in low-to-mid-complexity fast-to-implement features like code-review agents. So in case of linear and cursor-bugbot it make a lot of sense. I wonder when Github/Gitlab/Atlassian or Xcode will release their own review agent.

In our case, agentastic.dev, we just baked the code-review right into our IDE. It just packages the diff for the agent, with some prompt, and sends it out to different agent choice (whether claude, codex) in parallel. The reason our users like it so much is because they don't need to pay extra for code-review anymore. Hard to beat free add-on, and cherry on top is you don't need to read a freaking poems.

https://assets.agentastic.ai/agentastic-dev-assets/videos/0....

Part that i can't wrap my head around was at least in case of twitter, it was a hostile take over. In case of Vimeo, it didn't look hostile at all.

Is there a limit on number of instances you can have per physical mac? i recall there was a hard limit of 2 because of EULA, unless Apple has changed it. (Cupertino really likes to sell you their Macs)

Once coding agents become trivial, few people will know the detail of the programming language and make sure intent is correctly transformed to code, and the majority will focus on different objectives and take LLM programming for granted.

$AGENTASTIC_BRANCH $AGENTASTIC_BASE_BRANCH $AGENTASTIC_WORKTREE_PATH $AGENTASTIC_MAIN_REPO_PATH $AGENTASTIC_COMMIT $AGENTASTIC_REPO_NAME

if you give me some examples, i see i can also add that.

if you folks like to run parallel claude-code sessions, and like native terminal like Ghostty, i have a solution for using Git Worktree natively with Ghostty, it is called agentastic.dev, and it has a built-in Worktree/IDE/Diff/Codereview around Ghostty (macos only for now).

Would be happy to answer any questions

ShowHN post: https://news.ycombinator.com/item?id=46501758