🛠️ All DevTools

Exercise intensity influences body composition in healthy older adults (2025)

Database Traffic Control

Show HN: Gitstock–Transform you GitHub commit history into K-line and animations

[DevOps] Show HN: Agentic Orchestrator, a TUI for long-running coding agents Hello Folks!<p>Agentic Orchestrator is a terminal tool that takes complex feature requests and builds them by orchestrating coding agents through a series of phases that emulate a full-fledged engineering flow: requirements clarification, research, design, multi-phase planning, implementation, and review. It is a single pane of glass for all your features and exposes post-publish utilities such as resolving merge conflicts and responding to review comments.<p>The key design choice is that this is deterministic orchestration on top of undeterministic agents: things like &quot;human review gates&quot;, phase transitions, and artifact validations are all done by the harness in GO, while the agents take on &quot;bite-sized&quot; tasks.<p>In the lifecycle of a feature, human judgment is typically needed during the &quot;first half&quot; of the workflow (from clarification to planning), depending on how much the developer wants to be involved. The &quot;second half&quot; (multi-phased implementation&#x2F;review loop) typically executes while &quot;AFK&quot; unless the tool is unable to make progress without human intervention.<p>Agentic Orchestrator is Apache2.0 and can be installed via Homebrew. You should be able to run it on macOS, Linux and WSL as long as you have `gh` and at least one of the following coding agents: OpenCode (tested with GLM-5.2), Codex, or Claude Code. While having a single coding agent is enough, in my setup I like to mix and match different agents&#x2F;models for different phases (eg: claude&#x2F;opus4.7 for planning, opencode&#x2F;glm5.2 for implementing, codex&#x2F;gpt5.5 for reviewing).<p>I hope you enjoy it. Happy to answer any questions!

[Database] Letos: Create, edit, browse SQLite databases. Formerly known as SQLiteStudio

[Other] Show HN: AMA2, messenger built for AI agent I&#x27;m a solo founder building AMA2, a messaging runtime made for AI agents. This is my first Show HN, so I&#x27;d really appreciate your feedback.<p>What brought me this idea: At first, I was building an AI agent for solo creators that knows everything about you and can do business chore on your behalf. When I tried to plug it into normal chat tools like Telegram, Discord, Slack... , they all felt wrong for agents: 1. They don&#x27;t care about an agent&#x27;s context. To follow a thread, the agent has to pull the whole history every time. 2. Giving each agent its own account is painful. If you have (or will have) many agents, it would take forever. 3. Agents have limited permissions, so they can&#x27;t really reach out to someone (including agents) or make a connection on their own. (Yes, they should be controlled, but they still need a bit more room. Or full permissions with tight harness.) So I decided to build a messaging runtime where agents are first-class participants, like humans.<p>What AMA2 is: A messaging runtime, plus a web app to monitor and talk to your agents, plus public surfaces for agents (CLI, MCP). The thing I care most about is memory. Every thread has a thread memory, and every pair of participants has a relationship memory. These get built daily, and when an agent reads its messages through the CLI or MCP it gets those memories back, so it keeps the right context instead of replaying the whole history. Once you have an account, you can create an agent account in one click, and each agent account gets a public link, so anyone (human or agent) can message it.<p>Where it&#x27;s at: AMA2 just shipped. Right now I&#x27;m looking for test users who actively work with agents, and I&#x27;m building use cases myself: 1. My own agent team is using AMA2 and uses it like Slack. Every agent is a Claude Code instance, separated by project directory. You can check the guide here <a href="https:&#x2F;&#x2F;github.com&#x2F;ama2-team&#x2F;ama2-public&#x2F;tree&#x2F;main&#x2F;examples&#x2F;agent-team" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;ama2-team&#x2F;ama2-public&#x2F;tree&#x2F;main&#x2F;examples&#x2F;...</a> 2. I use my assistant agent&#x27;s public link instead of an email address. 3. I&#x27;m working on orchestration for an agent engineering team and will share that guide soon.<p>I think there are a lot more use cases here. AMA2 is just a messaging runtime, but I believe it can give you and your agents real leverage. It really depends on how you and your agents use it. If you have an idea or a use case you&#x27;d like to test, tell me and I&#x27;ll hand you a free subscription to try. And any feedback would be really appreciated.<p>One heads-up: there&#x27;s no playground yet, you do need a sign up to use it. Sorry about that.

[IDE/Editor] Show HN: Dribble – an open-source AI IDE for databases

Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity

Compiler-Assisted Floating-Point Error Analysis and Profiling with FPChecker

How working with a blind client revealed invisible accessibility gaps

[Other] You really shouldn't copy-paste errors into Claude Code

[Other] Show HN: Fleet – a local-first console for managing Dockerized Hermes AI Agents

Segmenting Robot Video into Actionable Subtasks

[API/SDK] Micro-Agent: Beat Frontier Models with Collaboration Inside Model API

The Wisdom of Quinn the Eskimo (Apple Developer Technical Support Engineer)

[Other] Ornith-1.0: self-improving open-source models for agentic coding

Obfuscation: Building the final boss of cryptography (Part I)

Cowboys, Frontiersmen, Settlers, Townspeople, Cityfolk

[Other] WSL container is now available for public preview

Show HN: PMB – local memory for coding agents that shows if it is used