If you're working on agents—or just exploring what’s possible—we open-sourced everything: github.com/augmentcode/...
GitHub - augmentcode/augment-swebench-agent: The #1 open-source SWE-bench Verified implementation
The #1 open-source SWE-bench Verified implementation - augmentcode/augment-swebench-agent
github.com
April 23, 2025 at 2:32 PM
If you're working on agents—or just exploring what’s possible—we open-sourced everything: github.com/augmentcode/...
FYI you should be using the responses API if you’re using openai
it’s a higher level API, so it’s just plain easier to work with, but also they’ve done a ton of optimization
for one — you’re part of the outer loop. reasoning and tool calls stream back interleaved, like in chatgpt
it’s a higher level API, so it’s just plain easier to work with, but also they’ve done a ton of optimization
for one — you’re part of the outer loop. reasoning and tool calls stream back interleaved, like in chatgpt
August 20, 2025 at 1:09 AM
FYI you should be using the responses API if you’re using openai
it’s a higher level API, so it’s just plain easier to work with, but also they’ve done a ton of optimization
for one — you’re part of the outer loop. reasoning and tool calls stream back interleaved, like in chatgpt
it’s a higher level API, so it’s just plain easier to work with, but also they’ve done a ton of optimization
for one — you’re part of the outer loop. reasoning and tool calls stream back interleaved, like in chatgpt
For those of you that don't have time to play around, the 3 top coding agents today are 1. ClaudeCode 2. AugmentCode 3. OpenCode
July 6, 2025 at 2:08 PM
For those of you that don't have time to play around, the 3 top coding agents today are 1. ClaudeCode 2. AugmentCode 3. OpenCode
not loyal to tools, loyal to shipping
switching from @augmentcode to @GitHubCopilot
just much cheper for usage
#buildinpublic
switching from @augmentcode to @GitHubCopilot
just much cheper for usage
#buildinpublic
March 7, 2026 at 11:00 AM
not loyal to tools, loyal to shipping
switching from @augmentcode to @GitHubCopilot
just much cheper for usage
#buildinpublic
switching from @augmentcode to @GitHubCopilot
just much cheper for usage
#buildinpublic
Bring AI Coding to Vim & Neovim with AugmentCode – A Cursor Alternative!
📖 Read the full guide (Pro members only):
👉 pro.tecmint.com/blog/augment...
Follow @tecmint.bsky.social for more #Linux and AI dev hacks!
📖 Read the full guide (Pro members only):
👉 pro.tecmint.com/blog/augment...
Follow @tecmint.bsky.social for more #Linux and AI dev hacks!
Bring AI Code Suggestions to Vim & Neovim - Like Cursor AI
This guide explains how to bring the Cursor experience to Vim and Neovim using the AugmentCode plugin
pro.tecmint.com
June 17, 2025 at 7:35 AM
Bring AI Coding to Vim & Neovim with AugmentCode – A Cursor Alternative!
📖 Read the full guide (Pro members only):
👉 pro.tecmint.com/blog/augment...
Follow @tecmint.bsky.social for more #Linux and AI dev hacks!
📖 Read the full guide (Pro members only):
👉 pro.tecmint.com/blog/augment...
Follow @tecmint.bsky.social for more #Linux and AI dev hacks!
Augment.vim: AI Chat and completion in Vim and Neovim https://github.com/augmentcode/augment.vim (https://news.ycombinator.com/item?id=43097814)
GitHub - augmentcode/augment.vim
Contribute to augmentcode/augment.vim development by creating an account on GitHub.
github.com
February 19, 2025 at 4:20 AM
Augment.vim: AI Chat and completion in Vim and Neovim https://github.com/augmentcode/augment.vim (https://news.ycombinator.com/item?id=43097814)
Augment.vim: AI Chat and completion in Vim and Neovim Discussion
GitHub - augmentcode/augment.vim
Contribute to augmentcode/augment.vim development by creating an account on GitHub.
github.com
February 19, 2025 at 3:20 AM
Augment.vim: AI Chat and completion in Vim and Neovim Discussion
So close to clicking on this #augmentcode not #claudecode
June 6, 2025 at 12:36 PM
So close to clicking on this #augmentcode not #claudecode
Ruler v0.2.9: Revert & AugmentCode
- Support for AugmentCode
- Revert command
Both contributed by @abhishek_a_i
Ruler is a CLI tool for developers and teams who work with multiple coding agents in the same codebase.
github.com/intellectro...
- Support for AugmentCode
- Revert command
Both contributed by @abhishek_a_i
Ruler is a CLI tool for developers and teams who work with multiple coding agents in the same codebase.
github.com/intellectro...
Release v0.2.9 · intellectronica/ruler
What's Changed
Initial augmentcode support for guidlines and mcp config by @abhishekbhakat in #47
revert command for cleanup by @abhishekbhakat in #48
New Contributors
@abhishekbhakat made t...
github.com
July 10, 2025 at 11:50 AM
Ruler v0.2.9: Revert & AugmentCode
- Support for AugmentCode
- Revert command
Both contributed by @abhishek_a_i
Ruler is a CLI tool for developers and teams who work with multiple coding agents in the same codebase.
github.com/intellectro...
- Support for AugmentCode
- Revert command
Both contributed by @abhishek_a_i
Ruler is a CLI tool for developers and teams who work with multiple coding agents in the same codebase.
github.com/intellectro...
🧵 We just released the #1 open-source agent on the SWE-bench Verified leaderboard by assembling the best of Claude Sonnet 3.7 and O1.
Open-source repo here: github.com/augmentcode/...
Here's how we achieved 65.4% success rate on the hardest coding benchmark in the industry: 🧠👇
Open-source repo here: github.com/augmentcode/...
Here's how we achieved 65.4% success rate on the hardest coding benchmark in the industry: 🧠👇
March 31, 2025 at 9:30 PM
🧵 We just released the #1 open-source agent on the SWE-bench Verified leaderboard by assembling the best of Claude Sonnet 3.7 and O1.
Open-source repo here: github.com/augmentcode/...
Here's how we achieved 65.4% success rate on the hardest coding benchmark in the industry: 🧠👇
Open-source repo here: github.com/augmentcode/...
Here's how we achieved 65.4% success rate on the hardest coding benchmark in the industry: 🧠👇
I gave AI one prompt.
It wrote 100% of the code.
Part 2: Does it actually work?
Debugging, demoing, and showing you exactly what
@augmentcode produced from a single prompt.
No hype. Just reality.
🔗 youtu.be/sWCJsvWYark
#VibeCoding @expo.dev
#AIAssistedDevelopment #ReactNative #BuildInPublic
It wrote 100% of the code.
Part 2: Does it actually work?
Debugging, demoing, and showing you exactly what
@augmentcode produced from a single prompt.
No hype. Just reality.
🔗 youtu.be/sWCJsvWYark
#VibeCoding @expo.dev
#AIAssistedDevelopment #ReactNative #BuildInPublic
One Prompt → Full React Native App: Debugging & Demo (VibeCoding Part 2 - Todo App)
YouTube video by Frank von Hoven
youtu.be
February 7, 2026 at 3:52 PM
I gave AI one prompt.
It wrote 100% of the code.
Part 2: Does it actually work?
Debugging, demoing, and showing you exactly what
@augmentcode produced from a single prompt.
No hype. Just reality.
🔗 youtu.be/sWCJsvWYark
#VibeCoding @expo.dev
#AIAssistedDevelopment #ReactNative #BuildInPublic
It wrote 100% of the code.
Part 2: Does it actually work?
Debugging, demoing, and showing you exactly what
@augmentcode produced from a single prompt.
No hype. Just reality.
🔗 youtu.be/sWCJsvWYark
#VibeCoding @expo.dev
#AIAssistedDevelopment #ReactNative #BuildInPublic
Want to see MCP in action? Learn how to orchestrate OpenAI agents using MCP, AugmentCode, and Qdrant.
📅 April 29 @ 11 am ET
🔗 Save your spot: try.qdrant.tech/mcp-agent-in...
📅 April 29 @ 11 am ET
🔗 Save your spot: try.qdrant.tech/mcp-agent-in...
April 14, 2025 at 5:21 PM
Want to see MCP in action? Learn how to orchestrate OpenAI agents using MCP, AugmentCode, and Qdrant.
📅 April 29 @ 11 am ET
🔗 Save your spot: try.qdrant.tech/mcp-agent-in...
📅 April 29 @ 11 am ET
🔗 Save your spot: try.qdrant.tech/mcp-agent-in...
Want to see our exact approach?
We've open-sourced our agent implementation and infrastructure here: github.com/augmentcode/...
Read the story: www.augmentcode.com/blog/1-open-...
We've open-sourced our agent implementation and infrastructure here: github.com/augmentcode/...
Read the story: www.augmentcode.com/blog/1-open-...
#1 open-source agent on SWE-Bench Verified by combining Claude 3.7 and O1
www.augmentcode.com
March 31, 2025 at 9:30 PM
Want to see our exact approach?
We've open-sourced our agent implementation and infrastructure here: github.com/augmentcode/...
Read the story: www.augmentcode.com/blog/1-open-...
We've open-sourced our agent implementation and infrastructure here: github.com/augmentcode/...
Read the story: www.augmentcode.com/blog/1-open-...
After working closely again with #AugmentCode for another day, I must say the feeling is *relief*.
It was able to completely and quickly fix the things that KiloCode+Claude completely messed up, along with other improvements. Well done, @augmentcode.com
It was able to completely and quickly fix the things that KiloCode+Claude completely messed up, along with other improvements. Well done, @augmentcode.com
I switched to #ClaudeAI via #KiloCode for about a week, and after having to top up my credits regularly, I feel I got almost zero value from it.
It is a poor imitation of #AugmentCode which gets things right the first time, most times. Highly recommended. Also, cheaper in the long run, by far.
It is a poor imitation of #AugmentCode which gets things right the first time, most times. Highly recommended. Also, cheaper in the long run, by far.
July 11, 2025 at 4:35 PM
After working closely again with #AugmentCode for another day, I must say the feeling is *relief*.
It was able to completely and quickly fix the things that KiloCode+Claude completely messed up, along with other improvements. Well done, @augmentcode.com
It was able to completely and quickly fix the things that KiloCode+Claude completely messed up, along with other improvements. Well done, @augmentcode.com
I need to correct something I posted earlier. I was using #ClaudeAI indirectly through #KiloCode and for whatever reason, it was making bad choices. I switched to #AugmentCode and it was much better. But since, I have tried Claude Code CLI and it is SOOO good, especially across folders.
September 8, 2025 at 3:03 PM
I need to correct something I posted earlier. I was using #ClaudeAI indirectly through #KiloCode and for whatever reason, it was making bad choices. I switched to #AugmentCode and it was much better. But since, I have tried Claude Code CLI and it is SOOO good, especially across folders.
I switched to #ClaudeAI via #KiloCode for about a week, and after having to top up my credits regularly, I feel I got almost zero value from it.
It is a poor imitation of #AugmentCode which gets things right the first time, most times. Highly recommended. Also, cheaper in the long run, by far.
It is a poor imitation of #AugmentCode which gets things right the first time, most times. Highly recommended. Also, cheaper in the long run, by far.
July 10, 2025 at 5:45 PM
I switched to #ClaudeAI via #KiloCode for about a week, and after having to top up my credits regularly, I feel I got almost zero value from it.
It is a poor imitation of #AugmentCode which gets things right the first time, most times. Highly recommended. Also, cheaper in the long run, by far.
It is a poor imitation of #AugmentCode which gets things right the first time, most times. Highly recommended. Also, cheaper in the long run, by far.
Ruler v0.3.9
- Copilot is now AGENTS.md exclusively (works both in the remote @GitHubCopilot and in @code)
- MCP support for Firebase Studio
- Doc updates
github.com/intellectro...
- Copilot is now AGENTS.md exclusively (works both in the remote @GitHubCopilot and in @code)
- MCP support for Firebase Studio
- Doc updates
github.com/intellectro...
Release v0.3.9 · intellectronica/ruler
What's Changed
Fix README accuracy issues: AugmentCode MCP support and CLI agents list order by @Copilot in #241
Remove vendor-specific Copilot output path, use only AGENTS.md by @intellectron...
github.com
September 19, 2025 at 3:51 PM
Ruler v0.3.9
- Copilot is now AGENTS.md exclusively (works both in the remote @GitHubCopilot and in @code)
- MCP support for Firebase Studio
- Doc updates
github.com/intellectro...
- Copilot is now AGENTS.md exclusively (works both in the remote @GitHubCopilot and in @code)
- MCP support for Firebase Studio
- Doc updates
github.com/intellectro...
Using #AugmentCode is very much like having a really REALLY smart & knowledgeable Junior developer that you just need to tell, in very loose and easy terms, how to proceed. Using it as an AI agent in #VSCode is a much better experience than others, so much that I've set it to Auto so it can just go.
July 11, 2025 at 4:35 PM
Using #AugmentCode is very much like having a really REALLY smart & knowledgeable Junior developer that you just need to tell, in very loose and easy terms, how to proceed. Using it as an AI agent in #VSCode is a much better experience than others, so much that I've set it to Auto so it can just go.
www.insightsfromanalytics.com/post/augment... @augmentcode.com #AugmentCode #AISoftwareDevelopment #DevOps #CodeCollaboration #AIforDevelopers #SoftwareEngineering
Augment Code: Revolutionizing AI-Assisted Software Development for Large Teams
Discover how Augment Code's AI platform revolutionizes software development for large teams, offering unparalleled codebase understanding and collaboration.In the rapidly evolving software development landscape, artificial intelligence has emerged as a game-changing tool for developers. However, as AI coding assistants become more prevalent, it's clear that not all solutions are created equal. Enter Augment Code, a pioneering company that's redefining what AI can do for large software engineerin
www.insightsfromanalytics.com
January 2, 2025 at 7:48 PM
Augment Code's smart indexing pipeline is a game-changer for large codebases! 40% faster retrieval with 99.9% accuracy, plus seamless fallback for new/changed code. As @augmentcode says: "AI for software doesn't just mean 'smarter' — it has to mean faster, too."
#DevTools #AI #CodeSearch
#DevTools #AI #CodeSearch
But fast search isn’t enough — codebases change constantly.
So we built a smart indexing pipeline that matches a live snapshot of your codebase…
…and transparently falls back to full search for new/changed code while a new index is built.
Augment Code has developed a smart indexing pipeline that significantly enhances search speed for large codebases, achieving over a 40% reduction in retrieval latency while maintaining 99.9% accuracy. The system utilizes approximate nearest neighbor (ANN) search through quantization, allowing for faster context retrieval in codebases exceeding 100 million lines of code. This innovative approach ensures that users receive relevant search results in real-time, even as codebases evolve, by seamlessly falling back to full search for new or changed code during indexing. As stated, 'AI for software doesn’t just mean “smarter” — it has to mean faster, too.'
x.com
July 5, 2025 at 12:03 AM
Augment Code's smart indexing pipeline is a game-changer for large codebases! 40% faster retrieval with 99.9% accuracy, plus seamless fallback for new/changed code. As @augmentcode says: "AI for software doesn't just mean 'smarter' — it has to mean faster, too."
#DevTools #AI #CodeSearch
#DevTools #AI #CodeSearch
Goodbye #Cursor?
#AugmentCode just changed the game with Tasklist.
Watch your #AI agent plan & track every step in complex builds — like a Twitter clone UI, live.
✅ Works with VS Code, JetBrains, Vim
✅ No more guessing, just control
Full demo 👇 youtu.be/a0S0HCIccVo
#AugmentCode just changed the game with Tasklist.
Watch your #AI agent plan & track every step in complex builds — like a Twitter clone UI, live.
✅ Works with VS Code, JetBrains, Vim
✅ No more guessing, just control
Full demo 👇 youtu.be/a0S0HCIccVo
Goodbye Cursor? Augment Code’s Tasklist Is a Game Changer for AI Coding Agents
YouTube video by Champion Edtech
youtu.be
July 30, 2025 at 5:19 AM
Goodbye #Cursor?
#AugmentCode just changed the game with Tasklist.
Watch your #AI agent plan & track every step in complex builds — like a Twitter clone UI, live.
✅ Works with VS Code, JetBrains, Vim
✅ No more guessing, just control
Full demo 👇 youtu.be/a0S0HCIccVo
#AugmentCode just changed the game with Tasklist.
Watch your #AI agent plan & track every step in complex builds — like a Twitter clone UI, live.
✅ Works with VS Code, JetBrains, Vim
✅ No more guessing, just control
Full demo 👇 youtu.be/a0S0HCIccVo
#AugmentCode as a developer assistant is the fastest darn coworker you could have. Multi-hour tasks are accomplished in seconds. And you can ask it the big picture architecture review questions too.
I am so very impressed. After 40+ years as a developer, my work pattern has fundamentally changed.
I am so very impressed. After 40+ years as a developer, my work pattern has fundamentally changed.
July 11, 2025 at 4:35 PM
#AugmentCode as a developer assistant is the fastest darn coworker you could have. Multi-hour tasks are accomplished in seconds. And you can ask it the big picture architecture review questions too.
I am so very impressed. After 40+ years as a developer, my work pattern has fundamentally changed.
I am so very impressed. After 40+ years as a developer, my work pattern has fundamentally changed.
AugmentCode is great for PR reviews. Expensive as hell though
January 4, 2026 at 10:46 PM
AugmentCode is great for PR reviews. Expensive as hell though
🚀 Augment Code: Free AI Coding Beast
SWE-bench Champion 🏆 | 200K Context | Master of Complex Codebases
Full Support for VS Code/JetBrains/Vim
"Faster than coworkers on Slack" - Collective VP of Engineering
Will you ditch Cursor to try it? 👀
#AI #AICode #AugmentCode
aidisruption.ai/p/ai-coding-...
SWE-bench Champion 🏆 | 200K Context | Master of Complex Codebases
Full Support for VS Code/JetBrains/Vim
"Faster than coworkers on Slack" - Collective VP of Engineering
Will you ditch Cursor to try it? 👀
#AI #AICode #AugmentCode
aidisruption.ai/p/ai-coding-...
AI Coding Augment (SWE-bench Winner) – Free for Complex Projects, Rivaling Cursor
Augment Code: AI for Large-Scale Projects – 200K Context, SWE-bench #1. Free trial now!
aidisruption.ai
April 8, 2025 at 3:30 PM
🚀 Augment Code: Free AI Coding Beast
SWE-bench Champion 🏆 | 200K Context | Master of Complex Codebases
Full Support for VS Code/JetBrains/Vim
"Faster than coworkers on Slack" - Collective VP of Engineering
Will you ditch Cursor to try it? 👀
#AI #AICode #AugmentCode
aidisruption.ai/p/ai-coding-...
SWE-bench Champion 🏆 | 200K Context | Master of Complex Codebases
Full Support for VS Code/JetBrains/Vim
"Faster than coworkers on Slack" - Collective VP of Engineering
Will you ditch Cursor to try it? 👀
#AI #AICode #AugmentCode
aidisruption.ai/p/ai-coding-...