ForgeCode - Worlds #1 Coding Agent

Every time you commit, there’s a tiny tax: 1. pause 2. think 3. summarize 4. write We removed it. `:commit` messages generated from your code changes instantly. Small feature. Surprisingly big impact.

You can now configure different models for your main agent, create commits, and suggest commands directly from your shell.

@NickSloggett Thanks for raising this. The page was outdated and has since been removed. Currently, we only support BYOK.

So @forgecodehq takes the cake in term bench - but pricing page has no frontier newest models? forgecode.dev/pricing/

@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/te…

@odysseus0z @jlongster Try @forgecodehq, built atop zsh.

@juniorro16 `:model` in zsh plugin or `\model` in cli

@forgecodehq How change a model? I select GLM-4.7, don't know how change to glm-5.

ForgeCode is now trending on GitHub in Rust and currently ranked #1 coding agent on TermBench.

@johncodes @jdegoes @opencode Fish isn't POSIX compliant 🙈

@jdegoes @opencode @forgecodehq > Built atop ZSH it's 2026: can we please have POSIX compatible terminal utilities? fish, bash fam rise up.

Unfortunately, @opencode's write tool consistently fails for large writes, giving agents no useful information, so they enter a doomloop not of their own making. Time to give @forgecodehq a try -- it's written in Rust, not TypeScript, which is a nice perk!

@mickcodez Appreciate that! 🙏 Curious, what would it take for us to become your daily driver?

@forgecodehq is a genuinely unique take on the coding harness... it won't be my daily driver but I will definitely use it!

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

@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.

We’re adding new agents to the Forge ecosystem. Alongside FORGE (implementation) and MUSE(planning), meet the new agents: PRIME– Documentation & blog review PARKER– Expert technical writer SAGE– Codebase research & exploration Smarter, faster, more complete workflows. Try them now with npx forgecode@latest

🚨 Model update @OpenAI 's - GPT-5, - GPT-5 Mini - GPT-5 Nano are now live on ForgeCode. Better tool calling compared to other OpenAI models, in our early tests. How does it compare to @claudeai's Sonnet 4? We’ll publish results soon.

@sama The new models are live on forgecode[.]dev Try it for free now & let us know what you think!

gpt-oss is a big deal; it is a state-of-the-art open-weights reasoning model, with strong real-world performance comparable to o4-mini, that you can run locally on your own computer (or phone with the smaller size). We believe this is the best and most usable open model in the world. We're excited to make this model, the result of billions of dollars of research, available to the world to get AI into the hands of the most people possible. We believe far more good than bad will come from it; for example, gpt-oss-120b performs about as well as o3 on challenging health issues. We have worked hard to mitigate the most serious safety issues, especially around biosecurity. gpt-oss models perform comparably to our frontier models on internal safety benchmarks. We believe in individual empowerment. Although we believe most people will want to use a convenient service like ChatGPT, people should be able to directly control and modify their own AI when they need to, and the privacy benefits are obvious. As part of this, we are quite hopeful that this release will enable new kinds of research and the creation of new kinds of products. We expect a meaningful uptick in the rate of innovation in our field, and for many more people to do important work than were able to before. OpenAI’s mission is to ensure AGI that benefits all of humanity. To that end, we are excited for the world to be building on an open AI stack created in the United States, based on democratic values, available for free to all and for wide benefit.

@sama The new GPT‑OSS models are now live on forgecode[.]dev Try them for free now on your terminal & let us know what you think!

gpt-oss is out! we made an open model that performs at the level of o4-mini and runs on a high-end laptop (WTF!!) (and a smaller one that runs on a phone). super proud of the team; big triumph of technology.

@sama @OpenAI

Just enabled gpt-oss-120B into ForgeCode. ✅Blazing quick, ✅Great with tool calls, ⚠️ It still run out of steam on long jobs. Next steps: Tweaking the prompts and will post our learnings. Big thanks to @sama and the @OpenAI team for open-sourcing the weights.

Try it out on: forgecode.dev