X Feed Intel

670

Relevant

263

Topics

1841

Total Posts

$1.088

Cost This Week

$1.088

Total Cost

2026-02-23T21:39

Last Fetch

← Back to Topics

Agents & Autonomy

OpenClaw autonomous agent with SSH and GitHub integration

Autonomous coding agent architecture deployed via OpenClaw inference platform with native SSH and GitHub access for self-directed development workflows.

14 posts · First seen 2026-02-23 · Last activity 2026-02-23

Time	Author	Post
2026-02-23T21:26	@trondw	Here’s the link to the OpenClaw skill I made for generating math worksheets. https://t.co/gKUPXr3f89 ↩ reply parent
2026-02-23T21:24	@DanielleFong	RT @MindaMyers: Open claw Agents develop strong local norms and respond to risky suggestions with norm enforcement, all without human overs…
2026-02-23T21:12	@agihouse_org	RT @summeryue0: Nothing humbles you like telling your OpenClaw “confirm before acting” and watching it speedrun deleting your inbox. I coul…
2026-02-23T21:05	@hwchase17	RT @LangChain_JS: Introducing https://t.co/z3Wlw6IVqu — a unified API reference for every @LangChain package across Python, JavaScript, Go…
2026-02-23T21:01	@TheTuringPost	RT @TheTuringPost: If you want to build your own OpenClaw-style AI agent, here’s a stack that can help you All are GitHub repos: Local Sc…
2026-02-23T20:48	@gregisenberg	how to use obsidian + claude code to build a 24/7 personal operating system and build your startup: 1. write everything in markdown (daily notes, projects, beliefs, people, meetings) 2. link your notes together so they mirror how your brain actually thinks. 3. install obsidian cli so claude code can read your entire vault + the relationships. 4. stop reexplaining projects every session. use reference files instead. 5. build custom slash commands: /context → load your full life + work state /trace → see how an idea evolved over months /connect → bridge two domains you’ve been circling /ideas → generate startup ideas from your vault /graduate → promote daily thoughts into real assets 6. keep a strict rule: human writes the vault. agents read it, suggest, execute. 7. let claude aka clode surface patterns you’ve been unconsciously circling for years. 8. delegate from inside your notes. one sentence in obsidian → agent handles the rest. 9. treat writing as leverage.the more you write, the more context your agents have. 10. understand this:markdown files are the oxygen of llms. i really enjoyed seeing how to use obsidian thanks to @internetvin vin uses ai like a thinking partner wired into his life’s work. 99.99% of people won’t do this because it requires reflection + setup. but once the vault exists, the agent stops being generic. it starts thinking in your voice. episode is live on @startupideaspod (more there) this one is different. send this tweet to a friend. im still processing how game changer obsidian + claude code is, maybe you too watch
2026-02-23T20:47	@ryxcommar	OK sell off your B2B SaaS holdings all you want but I'm not sure anyone aside from the biggest weirdo nerds is hooking up openclaw or whatever they're calling it now to their bank accounts for quite some time. My landlord still only takes rent with paper checks. https://t.co/TDqfL0viPt
2026-02-23T20:45	@migtissera	The signalling here was actually clear from the OpenClaw + OpenAI team-up. But it's (sort of) official now? With a name too: Agent Development Environment. You know, an OpenClaw-like AI agent as the primary agent that the user talks to, which can then orchestrate a Codex-like agent swarm is not too far off. I've been building this too, with my own personal agent, and I'm almost there. All the pieces you need are already there -- to start with, you can use the Codex App Server, which has a nice bidirectional JSON-RPC stdin/stdout pipe. You need to create a strong orchestrator on top that can handle spaw/kill/restarts, approvals, steering and verification. If I don't do this in time, OpenAI will do it anyway. Next 12 weeks is going to be crazy. Again, what a time!
2026-02-23T20:32	@romainhuet	Very excited to have @jxnlco join us at OpenAI! Jason is a true AI practitioner, shipping agents and running evals in production with dozens of customers. That hands-on experience will help us make agents and Codex better for builders. Welcome! 🙌 https://t.co/oK1h8yi815
2026-02-23T20:20	@WolframRvnwlf	Today's 🦞 @openclaw tip is as practical as it is simple - some easy but vital basics that surprisingly many people don't know: While the gateway UI displays all tool calls happening in the background, external interfaces like Telegram or WhatsApp don't. You can, however, enable verbose mode with a simple slash command (/v is a shorthand alias for /verbose): /v on I always enable it in a new session so I know exactly what's going on. If you want even more insight, use this to see not only the calls but also their results: /v full This way, if you notice your agent doing something it shouldn't, you can immediately stop it with this - the most important command of all: /stop Since that's a direct gateway command, not a message sent to the AI, it halts any running action instantly. With just these three commands, you're much better equipped to stay in control of your little claws.
2026-02-23T20:19	@iScienceLuvr	i'll admit i haven't tried OpenClaw yet cuz the security concerns are worrying https://t.co/5QX8HEIunG
2026-02-23T20:13	@DavidSKrueger	RT @summeryue0: Nothing humbles you like telling your OpenClaw “confirm before acting” and watching it speedrun deleting your inbox. I coul…
2026-02-23T19:31	@TheTuringPost	RT @TheTuringPost: 20 Awesome Github repos to build your own OpenClaw-style agents Local model runners ▪️ Ollama ▪️ vLLM Vector databases…
2026-02-23T19:00	@haltakov	The setup: 🦞 @openclaw running on a VPS (Tailscale private net) 🤖 Connected to GPT-5.3-Codex 💬 Talking to it via Telegram 🔑 It has its own SSH key and Github account That's it. Now I can build stuff from anywhere. ↩ reply parent