GitHub Projects Community (@GithubProjects) header
GitHub Projects Community (@GithubProjects) profile picture

We're sharing/showcasing best of @github projects/repos. Follow to stay in loop. Promoting Open-Source Contributions. UNOFFICIAL, but followed by github

San Francisco, CA
Joined October 2020
Photo by GitHub Projects Community (@GithubProjects)Photo by GitHub Projects Community (@GithubProjects)Photo by GitHub Projects Community (@GithubProjects)Photo by GitHub Projects Community (@GithubProjects)Photo by GitHub Projects Community (@GithubProjects)Photo by GitHub Projects Community (@GithubProjects)Photo by GitHub Projects Community (@GithubProjects)Photo by GitHub Projects Community (@GithubProjects)Photo by GitHub Projects Community (@GithubProjects)Photo by GitHub Projects Community (@GithubProjects)
Imagine texting your computer a task from anywhere and coming back to it already done. This open-source AI agent lets you call, text or message it from the apps you already use, and it keeps working long after you've walked away.
10
12
1
190
317,487
Open-source plugin makes Claude Code cheaper on repos you reuse Explore it here: osp.fyi/tokeneconomizer
2
31
4,465
Open-source monospace font for code, terminals, and technical documents with configurable character variants. Explore it here: osp.fyi/iosevka
1
4
44
5,273
The future they want?
3
10
4
68
8,094
When you take over a teammate's unfinished work, the ticket rarely tells the whole story. SWE-CoWork tests whether coding agents can do the same in a simulated workplace, recovering missing requirements from project docs, chats, and teammates before delivering patches evaluated by hidden tests across 101 tasks from 101 real open-source repositories.
Can a coding agent take over a teammate’s work in progress? Introducing SWE-CoWork, a benchmark for coding agents working as digital employees on long-horizon software engineering tasks. Each assignment starts with a short handoff in a simulated workplace modeled on real-world engineering workflows. Agents search task boards and versioned docs, ask teammates for missing details, and revise their code when a reply changes what needs to be built. Open questions and confirmed requirements can both be lost before the agent hands the work back. SWE-CoWork lets us trace them through the conversation, the patch, and the tests. 101 assignments across 101 real open-source repositories. 26 simulated teammates per workplace. 11 programming languages. 12 application domains. 17 workplace tools. 🌐 Website: tokenwave-ai.github.io/swe-c… 📄 Paper: arxiv.org/abs/2611.20218 💻 Code: github.com/TokenWave-AI/swe-… 🤗 Hugging Face Daily Papers: huggingface.co/papers/2611.2… (If you find it useful, we’d appreciate an upvote!)
2
23
5,179
Swim through a dreamy kelp forest in your browser tonight, with nothing to install and it works offline osp.fyi/abyssal-garden
1
1
31
6,330
Make your PS5, Xbox or PC footage sharper and smoother in real time on Windows, with no code to write. osp.fyi/veyra-nrvideo
4
11
4
252
22,930
Open-source trip planner you host yourself, with live maps and group planning Explore it here: osp.fyi/trek-10
3
24
336
17,047
Run lattice Boltzmann CFD on any GPU or CPU via OpenCL Explore it here: osp.fyi/fluidx3d
20
6,617
Pull articles from a web and get it as clean HTML or Markdown. Explore it here: osp.fyi/defuddle
2
5
106
9,787
The IRS's free tax-filing service, now open source
3
9
2
173
11,930
Keep your buy and sell calls yours, but make the review, risk and journaling steps repeatable with installable Claude Skills: Explore it: osp.fyi/claude-trading-skill…
1
21
254
13,574
Stream iOS simulators and Android emulators to any browser without installing Xcode or Android Studio.
4
37
1
501
22,774
Run your own message broker so devices and apps can publish and subscribe, then test it from the command line in one step osp.fyi/mosquitto
3
6
92
10,851
Karpo-Decision-31B: an open decision model that picks between options instead of generating text, and returns a calibrated probability for each one. Currently #1 on the Decision Index (73.9 Full) and ahead of Gemini Decision 1 on When2Call and Mind2Web. Inference code is public too. Weights: karpo.ai/models/decision
Picking the next tool shouldn’t take a paragraph. We built Karpo Decision. A family of six open-weight models, from 0.8B to 31B.Give it the context, a question, and the options. It returns a probability for each option in one forward pass. Karpo Decision 31B 🏆 73.9 on Decision Index, tied for #1 on the Nov 12 board ⚡ 94 ms median per request on a single RTX PRO 6000 📊 87.2 on JevBench Capability vs. 78.5 for Google’s Gemini Decision 1 🤗 Hugging Face huggingface.co/MachinePulseA… 📝 Technical write-up karpo.ai/blog/karpo-decision… Here’s where I’d try it first: Search. Recommendations. Tool choice. Model routing. Browser actions. Point it at the slowest decision in your stack and tell us what breaks.
1
4
94
32,120
A static browser chat interface for the DeepSeek API that keeps conversations and attachments on your device. Explore it here: osp.fyi/chat-demo
3
3
1
51
10,251
Use AI assistant inside Blender to inspect your scene, build objects and assign materials, without writing code osp.fyi/blender-ai-mcp-addon
2
32
8,384
AG-UI's open, lightweight protocol standardizes how agents stream chat, sync state, and render UI in real time.
4
1
37
8,879