secbear
secbear on Hacker News
Posted by
secbear on Tuesday February 24, 2026 @10:49AM
from the show-hn dept.
https://secbear.github.io/neuron/
The core of every agent framework is the same ReAct loop. It's commodity code. What actually matters is everything around that loop — how you manage context windows, how you pipeline tool execution, how you handle durability and replay. These are hard problems with real design trade-offs, and yet every framework bundles them into one monolith where you buy all of it or none of it.neuron is the...
Totally agree. I've found in many cases it's easier to roll your own software/patch existing software with AI than to open an issue, submit a PR, get it reviewed/merged, etc. Let alone buying software
seems pretty solid from a security perspective actually
wild, all the references to "pizza" are disturbing
Hard mode- constant auto-complete suggestions that are right ~50% of the time
The finding that self-generated skills provide negative benefit (-1.3pp) while curated skills give +16.2pp is the most interesting result here imo. Big discrepancy, but makes sense. Aligns with the thought that LLMs are better consumers of procedural knowledge than producers of it.
+4.5pp for software engineering is suspiciously low compared to +51.9pp for healthcare. I suspect this reflects that frontier models already have strong SWE priors from training data, so skills add less marginal value. If true, skills become most valuable precisely in the domains where models are weakest — which is where you'd actually want to deploy agents in production. That's encouraging.
I feel similar... OpenClaw has lots of vulnerabilities, and it's very messy, but it also brought self-hosted cron-based agentic workflows to your favorite messaging channel (iMessage, telegram, slack, WhatsApp, etc.), which shouldn't be overlooked
Nice, have you considered adding support for agents/commands as a part of these presets?
Agreed, my experience and code quality with claude code and agentic workflows has dramatically increased since investing in learning how to properly use these tools. Ralph Wiggum based approaches and HumanLayer's agents/commands (in their .claude/) have boosted my productivity the most.
https://github.com/snwfdhmp/awesome-ralph https://github.com/humanlayer
Amazing to see claude's reasoning and process through reversing this
Built this because I wanted Claude Code to run untrusted snippets without touching my system, but Docker felt heavy. Uses jail.nix (bubblewrap) for isolation. Currently supports Python, Node, Bash with persistent REPL sessions.
Would love feedback on the interface design.
Posted by
secbear on Monday February 09, 2026 @01:07PM
from the show-hn dept.