@Code_With_James

Sharing cool AI & GitHub finds for devs who build. DMs open—let’s see what you’re building.

 Somewhere in your GitHub stars
Joined February 2025
  • Tweets299
  • Following249
  • Followers45
25Media
James retweeted
Liam
@liamsplaybookApr 16
Replying to @karpathy
@karpathy said "Obsidian is the IDE, the LLM is the programmer, the wiki is the codebase." @garrytan built GBrain, 17,000 pages of personal knowledge. I loved this idea. But I wanted it without the setup. So I built Thinkly: paste any AI chat, and the wiki builds itself.
Garry Tan
@garrytanApr 10
If you want your OpenClaw or Hermes Agent to be able to have perfect total recall of all 10,000+ markdown files, GBrain is here to help. It's exactly my OpenClaw/Hermes Agent setup. MIT-licensed open source. Hope it helps you build your mini-AGI. github.com/garrytan/gbrain

GitHub - garrytan/gbrain: Garry's Opinionated OpenClaw/Hermes Agent Brain

Garry's Opinionated OpenClaw/Hermes Agent Brain. Contribute to garrytan/gbrain development by creating an account on GitHub.

github.com
2
5
8
854
James retweeted
myinc@trymyincApr 16
New flow: paste links, get a published page. 30 seconds ago, this was 5 article links. Now it's a published Research Summary. Paste → pick a template → publish.
1
2
4
47

🧵 Why Most AI Agents Fail at Personal Knowledge (And how to actually fix it)

Article · @pluglab_ai
5
1
9
203
We’re rolling out a few updates to Codex today: 1. Codex is rolling out to ChatGPT Plus users today. It includes generous usage limits for a limited time, but during periods of high demand, we might set rate limits for Plus users so that Codex remains widely available.
84
264
116
2,280
1,307,862
Focus beats frenzy. - Launch small - Tune out the noise - Learn as you go - Show up consistently - Question your process Slow growth wins in the long run.
1
7
121
Still no traction? That’s not failure. That’s setup. The quiet commits. The edge-case fixes. The 1-line deploys. That’s real progress. Keep shipping. Compounding doesn’t make noise.
1
1
4
211
Bugs don’t wait. Launch dates don’t wait. Users don’t wait. Ignore the clock. Ship the code.
1
4
45
Think like an engineer. Move like a builder. Decide like an owner.
1
8
126
Clients don’t wait. Models don’t slow down. Competition won’t pause. Forget the clock. Ship anyway.
1
1
7
143
Live with intention. - Build quietly - Reflect often - Test quickly - Move daily - Think deeply Steady momentum outlasts noisy distraction.
3
1
7
440
Deadlines don’t wait. Algorithms don’t pause. Markets don’t care. Forget the calendar. Build anyway.
1
8
346
Boring habits build powerful lives. - Coding when it’s quiet - Reading instead of scrolling - Writing to think - Walking to reset - Shipping before you're ready Fun is optional. Progress isn’t.
1
8
237
Live a focused life. - Coding -Journaling -Iterating -Walking -Thinking Quiet momentum beats loud chaos.
1
1
13
210
Big news: VS Code just made AI agent workflows smoother. You can now manage tool approvals via a simple dropdown: – per session – per workspace – or globally A small UX touch that saves real friction.
1
5
78
Feeling behind? You’re not supposed to peak in your 20s. Most millionaires hit that mark in their 50s—after decades of learning, building, and stacking skills. Play long-term games. The timeline is on your side.
1
6
381
TextArena is now on Hugging Face 57+ competitive text games to test LLMs on negotiation, deception, and planning. Supports multiplayer, TrueSkill, and human-vs-model play.
https://huggingface.co/papers/2504.11442

ALT https://huggingface.co/papers/2504.11442

1
1
6
108
AI learns from your patterns. Keeps what works. Skips what doesn’t. Your code history trains your future assistant.
1
6
1,105
Collected some of the best MCP servers in one place.
1
5
75
Hi3DGen: Images to high-fidelity 3D models, powered by AI.
1
5
272
SpatialLM is incredible! This AI instantly transforms basic videos into precise 3D layouts and floorplans. Curious about how it operates and how to get started? Details below 👇
1
5
189
Load more