runanywhere-sdks / core
AGENTS.md10k starsChanged 13 days agoLicence not identifiedView on GitHub
See the repo-root AGENTS.md first for cross-cutting rules (business-logic layering, iOS-as-source-of-truth, workflow conventions) — this file adds only what is specific to core/, the C/C++ commons library. - C++20 standard…
Trending
More talk lately.thin dataabout the whole repository
Who's talking about RunanywhereAI/runanywhere-sdks
- Singh in USA“I Left $200k+ Job at Intuit to Build THIS! (Viral YC Journey)”YouTube · Feb 11, 2026 · 5.9k views
- RunAnywhere“Meet the New RunAnywhere”YouTube · Jul 13, 2026 · 88 views
- safesynt“RunAnywhere runs LLMs locally on your phone”YouTube · Nov 11, 2026 · 43 views
- thezakulo“Local AI just stopped being a science project.”YouTube · Sep 23, 2026 · 19 views
- A Hacker News story“Runanywhere – Make every CPU and GPU count”Hacker News · Aug 20, 2025 · 5 points
The biggest 5 of 13 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 13
Talked about on GitHub, YouTube and Hacker News (13 times).
On GitHub · 8
- Sep 22, 2026fix: restore local coding harnesses and polish CLI help — RunanywhereAI/wally0 reactions · 6 comments
- Aug 13, 2026Add LiquidAI LFM2.5-VL-3B to the model catalog, and move to SDK 0.20.18 via runanywhere-swift — RunanywhereAI/runanywhere-ios0 reactions · 6 comments
- Mar 16, 2026[WIP] Add web-based AI English speaking practice assistant — roshan-engineer/english_bot0 reactions
- Mar 10, 2026[Bug]: VAD not working properly and github action — shreyaspapi/Oval0 reactions
- Feb 7, 2026Add RunAnywhere SDK for on-device mobile AI — EthicalML/awesome-production-agentic-systems0 reactions
3 more on GitHub
- Feb 7, 2026[WIP] Add Runanywhere SDKs to the project — EthicalML/awesome-production-machine-learning0 reactions
- Jan 30, 2026Add RunAnywhere AI TTS Integration as Third Playback Option — answersolutionsapps/runandread-ios0 reactions
- Nov 27, 2025feat: you can now run local transcription models instead of calling OpenAI whisper — rami-maalouf/audora0 reactions · 1 comment
On YouTube · 4
- Feb 11, 2026I Left $200k+ Job at Intuit to Build THIS! (Viral YC Journey) — Singh in USA5.9k views · 9 comments
- Jul 13, 2026Meet the New RunAnywhere — RunAnywhere88 views · 1 comment
- Nov 11, 2026RunAnywhere runs LLMs locally on your phone — safesynt43 views
- Sep 23, 2026Local AI just stopped being a science project. — thezakulo19 views
On Hacker News · 1
- Aug 20, 2025Runanywhere – Make every CPU and GPU count5 points · 2 comments
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- engines/AGENTS.mdAGENTS.md
- idl/AGENTS.mdAGENTS.md
- runtimes/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- engine-plugin-authoringSkill
- sdk-publishSkill
- sdk-releaseSkill
- sdk-test-startersSkill
- telemetry-e2eSkill
- engine-plugin-authoringSkill
- sdk-publishSkill
- sdk-releaseSkill
- sdk-test-startersSkill
- telemetry-e2eSkill
The file
We split this AGENTS.md into the rules it gives an agent
5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.