162 karma · joined February 5, 2019
https://carelesswhisper.app https://voicebraindump.com
https://github.com/srv1n/kurpod/pkgs/container/kurpod-server
wasm version compiles to under a MB though!
Skills have the scripts folder and you can precisely describe when and when not to use a script. This can end up directly wrapping API(s), CLIs, generic scripts or even other MCP servers.
CC and codex both have the skill creator and you can have them build the skill for you.
Havent run into any scenarios where skills were missing tools. 1-2 iterations and its usually taken care off quite quickly.
OpenClaw, Hermes and other agents have already made skill adoption mainstream?
Are you guys still seeing a future where people are dumping entire MCP tool defs into context?
But the funding chain here is -
Major coffee companies illy | JDE Peet's | Lavazza | Paulig | Tchibo
↓
↓
↓
I read the blog post and your website but unfortunately didnt help change my perspective.
Thanks for the share
Do you have any good demos to showcase where graph DBs clearly have an advantage? Its mostly just toy made demos.
vector embeddings on the other hand no matter how limited clearly have proven themselves useful beyond youtube/linkedin thought leader demos.
1. Airpods or ANC
2. WFH ->. Less movement -> stiff muscles around neck and head -> head trasnfer frequencies changing
3. Covid vaccine
Managed to make long dictations even >10mins appear in < 2seconds by pushing what is possible with current STT models.
All processing done locally with 0 network calls.
I use it as a context fetcher i.e grab an abstract/transcript/thread as clean text/JSON, pipe it into summaries or scripts.
Also runs as an MCP server (experimental), so tools like Claude Desktop or CLI assistants can call the connectors directly.
arivu fetch hn:38500000
arivu fetch PMID:12345678
arivu fetch https://arxiv.org/abs/2301.07041
Just curious. Especially with both OpenAI and Anthropic really also outpacing startups in release cadence unlike previous cycles.
Guessing your selling point is any model no locking (Assuming we are happy with the privacy SOC 2 etc guarantees on enterprise contracts here)
I have a lot of actions done but not full there yet. Essentially the goal is to use a cli or an external desktop app to drive your already logged‑in Chrome profile without navigator.webdriver, or enabling --remote‑debugging‑port. In all my testing never got flagged with captcha/bot protect. The cli can interact with LLMs, local file system(despite opfs this is easier).
CLI(host app) <-> Native messaging daemon <-> Chrome extension
Extenion just executes pure js for extraction, navigation. Ive gotten basic google searching, image downloading working. Looking at complex form interactions.
1. I see the core is OSS, any chance of it being pushed up on crates.io(i see you already have a placeholder)
2. Is it embeddable or only as a Axum server?
Do you see all providers converging on similar alpha i.e cheap object storage, nvme drives,ssd cache to solve this?
Cheers and congrats on the launch
Lets you hide 1000s of images, pdfs, videos, secrets, keys into a single portable innocent file like "Vacation_Summer_2024.mp4".
Low friction Markdown based voice journaling.