ForgeCode - Software Factory retweeted
If you are at @_TechSparks, go to ForgeCode booth and play a cool game
@go2peach is in the leader board.
@forgecodehq @amitksingh1490 @ashprakasan @MadhanK50528089
ForgeCode - Software Factory retweeted
I built the open source codex app!
One of my favorite features is “Workspaces” - reusable multi-chat layouts you can save and switch between depending on the task.
Built on top of @forgecodehq
ForgeCode - Software Factory retweeted
Have a look at the leaderboard in terminal bench @forgecodehq really shining. Codex with gpt5.5 hits 82% whereas forgecode hits 81.80% with gpt5.4.
ForgeCode - Software Factory retweeted
Is the real bottleneck for AI agents the model—or the harness?
Terminal-Bench 2.0 suggests it might be the latter. ForgeCode ranks #1 among open-source harnesses, showing how much performance you can unlock without changing the model—just by improving how it uses tools.
In ForgeCode’s case, the gains come from better tool orchestration and execution.
Learn more: tensorlake.ai/blog/forgecode…
ForgeCode - Software Factory retweeted
Days ago, I was checking out the once VERY relevant terminal bench. I kept seeing this Agent called @forgecodehq always in the top 5.
Decided to try it and never looked back. It's now my daily ai-enhanced terminal.
Feature packed, but not stuffed to the gills. I love it!
ForgeCode - Software Factory retweeted
After 2 months our #1 rank on Termbench was finally broken by a worth competitor (by 0.2%) 🙌
If someone from @OpenAI can help us in getting unrestricted API access, that'd be great! We'd love to run to on @forgecodehq and share notes 😇
ForgeCode - Software Factory retweeted
🚀 Excited to see ForgeCode @forgecodehq now supporting Novita AI as a built-in provider.
Developers can now use frontier open-source coding models like Kimi-K2.5, GLM-5, and MiniMax-M2.5 directly inside their terminal workflow.
No adapters. No workflow changes.
Just:
:login → choose Novita
:model → pick your model
start shipping ⚡
Why this matters:
→ terminal-native coding workflow
→ instant model switching across providers
→ context preserved across sessions
→ lower-cost coding workloads
→ pay only for what you use
For developers living in Zsh, Warp, and terminal-native IDE workflows, this means faster agentic coding with better model economics.
Full setup guide 👇
blogs.novita.ai/use-novita-a…
Try it in your next coding session ⚡
ForgeCode - Software Factory retweeted
I love this framing 👇
@theo clearly breaks down the difference between an Agent Harness and an ADE (Agentic Developer Environment).
ADEs should support multiple harnesses, built on open protocols like ACP.
Harnesses, on the other hand, should be:
lightweight
high-performance
outcome-driven
I am really excited to bring @forgecodehq harness to T3 and beyond.
youtube.com/watch?v=hDn8-fK3…
ForgeCode - Software Factory retweeted
Replying to @gdb
5.4 is insanely good for coding. We've been benchmarking it and are surprised by how strong it is. Kudos to the team for finding the right balance between intelligence and speed 🙌
tbench.ai/leaderboard/termin…
ForgeCode - Software Factory retweeted
Replying to @odysseus0z @jlongster
Try @forgecodehq, built atop zsh.
ForgeCode - Software Factory retweeted
Men I really love Froge Code cli, it makes me excited to code with it!
@forgecodehq
Hope one day I build my own cli like theirs
ForgeCode - Software Factory retweeted
Replying to @forgecodehq
@forgecodehq is the #1 coding agent today.
We have 78.4% accuracy on TermBench 2.0, the global benchmark for terminal-based coding agents.
We did this with a very small team. You could almost count us on a horse’s hoof! It took a lot of time, and at many points it felt like we were chasing a goal that kept moving faster than us.
These benchmarks are quite literally the Olympics of AI, where the world record resets every day. For now though, we’re the champions here.
And we’re not stopping.
More on how we got the score in our blog (link below)
This is just the beginning.
ForgeCode - Software Factory retweeted
Model tersedia
Sonnet 4
Gemini 2.5 Pro
Saat ini harganya: GRATIS
forgecode.dev/pricing/
ForgeCode - Software Factory retweeted
🚨 Claude Code is cool.. but what if you could pair program with every top model?
GPT-4o, Deepseek, Grok 4, Kimi 2, Gemini, Qwen… all inside your terminal.
Here’s why you should use different AI models: 👇
ForgeCode - Software Factory retweeted
Final Verdict 🏁
If I had to sum it up:
🥇 Best all-around: ForgeCode
🧠 Deep code understanding: Claude
⚡ Speed + polish: Gemini CLI
🔀 Most flexible: Aider
🔒 Safest local gen: Codex CLI
ForgeCode - Software Factory retweeted
I tested 5 AI Coding Agents in the Terminal — and what I found shocked me 🤯
From ForgeCode to Google Gemini CLI…
Which one writes better code? Which one gets your project?
Here’s the good, the weird, and the game-changing 🧵👇
#webdev #ai #javascript #cli
ForgeCode - Software Factory retweeted
You’ve probably heard the buzz around Grok 4, xAI’s newest AI model.
But is it really a step toward AGI, or just another overhyped release?
I broke it all down:
- Benchmarks
- Reasoning power
- Pricing + access
- Future Plans
Full deep dive 👇
ForgeCode - Software Factory retweeted
Replying to @Arindam_1729 @forgecodehq
really good🔥
I also tested it against Claude Code and Gemini CLI
generativeai.pub/ai-coding-s…



























