there's details on how other platforms can support it here: https://ai-daemons.com/spec/#provider-guide
- example daemon files: https://github.com/charlie-labs/daemons
- reference docs: https://docs.charlielabs.ai/daemons
happy to answer questions. all feedback appreciated.
compared to routines:
- daemons are specified by a DAEMON.md file in the repo (like skills). it's version-controlled and team-owned, not hidden in a dashboard or linked to a single developers account.
- daemons have a specialized event pipeline that joins similar webhooks events into a single daemon activation and can inject late arriving events into a daemon that's already running (this is key to avoid duplicate work and noisy actions).
- the watch conditions are a more powerful activation method because they use semantic matching and can be mixed with cron schedules.
- daemons have access to the logs from their past runs (and soon proper memory) so they can learn from their own mistakes.
For almost two years, we've been developing Charlie, a coding agent that is autonomous, cloud-based, and focused primarily on TypeScript development. During that time, the explosion in growth and development of LLMs and agents has surpassed even our initially very bullish prognosis. When we started Charlie, we were one of the only teams we knew fully relying on agents to build all of our code....
you could even have a daemon that just says to run an existing skill.
The UI is my own design system that I will open source at some point. The app is Remix with a Redis cache to keep things snappy.
My guess is that there are more relevant results from the semantic search than I'm including in the context (to reduce costs) and that exact snippet isn't being given to the answering model as context.
This is a quick prototype I built for semantic search and factual question answering using embeddings and GPT-3.It tries to solve the LLM hallucination issue by guiding it only to answer questions from the given context instead of making things up. If you ask something not covered in an episode, it should say that it doesn't know rather than providing a plausible, but potentially incorrect...
I was getting really sick of taking and sharing multiple screenshots every time I wanted to share a ChatGPT thread, so I made https://gpt.best/It's a minimal tool that creates shareable links [1] from ChatGPT conversations. It also has dynamic share images so you get a screenshot of the beginning of the thread for free.1: https://gpt.best/k5Q5F9Up
1. Salary range
2. Remote work policy
3. Tech stack
4. The product/team the role is for
Making a resume sucks, but it doesn't have to. With Standard Resume you can import your LinkedIn in one click, pick from 12 templates, and share it as a PDF, or web resume (great for casual applications and referrals).
It's a lightweight tech stack that I maintain myself. It's Firebase+React+Next, combined with a custom written PDF layout engine.
Web example: https://rsm.io/sidney-template
PDF example: https://assets.standardresume.co/image/upload/v1607879981/re...
"You hereby grant to Leet Resumes a non-exclusive, perpetual, irrevocable, royalty-free, fully paid-up, worldwide license (including the right to sublicense through multiple tiers) to use, reproduce, process, adapt, publicly perform, publicly display, modify, prepare compilations and derivative works of, publish, transmit and distribute your User Content, or any portion thereof, and to publish, transmit, distribute and sell compilations and derivative works of your User Content, in any form, medium or distribution method now known or hereafter existing, known or developed, without compensation to you."