Not yet published to npm — npx confessor won't work for others until the user runs npm publish. This gates the launch. <- When do you plan to do this? I was able to run it myself using the directions in the CLAUDE.md but shouldn't they be in thee README.md until it's published?
It's synced hourly, it uses the API from the 3rd party to determine what has changed and then ingests the changes, it's also how it cleans up the stale data.
For embeddings I am using Titan Text Embeddings V2
I built it to solve my own challenges with my consulting work and sales work. I kept building the same platform over and over to write my book, handle emails with customers, and sales reps, etc.. so I decided to make it a SaaS platform.
I use it personally every day to read my emails, generate drafts because RetriveIT has all the marketing material I have stored in gdrive and github. Sometimes I even use it for silly thigs like I'll ask it "what is my ITIN and what date did I register my company" because I hate having to search though gdrive to find that info when I need it.
It's technically different because unlike claude or chatgpt OAuth is bound at the workspace level not at the user level. A user can be a member of multiple workspaces, and users can share their workspace with other workspaces inside of an orginization.
There is a free signup on the site with email, it uses magic link.
But isn't that what Linux admins said when Cloud and Platform Engineering became a "thing".
Puppet, Chef, Ansible they are taking the fun out of system administration, Cloud it's going to take away my job. But what happened is roles changed, SRE, Platform Engineering, dare I say DevOps engineers (whatever those are) all emerged.
Software engineering is going through he same transformation with the same knee jerk reactions from both sides of the argument. Either AI run rampant with no guardrails like OpenClaw people burning 1000s in tokens, OpenClaw calling them randomly at 2am, etc.. then on the other side of the argument we have a petition asking the Node.js Technical Steering Committee to ban AI-assisted code from Node.js core.
AI is here, it's here to stay, I believe that those of us that will be successful will find the middle ground.
Not allowed? This is easy to find in the Agent SDK docs
"Unless previously approved, Anthropic does not allow third party developers to offer claude.ai login or rate limits for their products, including agents built on the Claude Agent SDK. Please use the API key authentication methods described in this document instead."
We saw this, but thought it was for Agents calling the API directly. Outworked is just a wrapper around your CLI using the existing agents and sub-agents in your Claude Code installation.
It's a great point though and we'll need to read into this more in-depth. Appreciate you raising this.
Right, pretty sure people got their accounts shut down for doing this kinda thing in the early days of OpenClaw before it was renamed and when it supported login. I guess you can take your chances but API is probably the only safe way to use this.
This is what we do for our own internal apps, what we do is actually much more complex we ingest all the docs from Github and Confluence AND we generate code-maps into a RAG then we expose it with an MCP, integrate that MCP into claude code so claude can ask for both our coding standards, IaC standards, testing standards, etc.. but also has the full context about the applications it needs to consume from or deliver to.
If we want AI assistants to contribute to a codebase like a productive member of the team, they need the same kind of context you’d give a new hire. Coding standards, infra conventions, testing patterns, and the shape of the system all matter.
We’re focused on a narrower version of that same problem.
First, we want to make it simple for any team to adopt a new library or SDK without reading a pile of docs or spending hours writing and debugging integration code. The goal is to make it easy for an agentic coding workflow to absorb a new API library quickly and use it correctly.
Second, a lot of teams are already maintaining their own AI context across AGENTS.md files, skills, and MCP servers. That means API providers, and really maintainers of any library at this point, need to provide a context layer that fits into what teams have already built. Adding a new dependency shouldn’t force every team to create and maintain a separate context layer just to consume that API well.
That’s the part we care about a lot: SDK context should be generated and maintained automatically, stay in sync with the SDK and docs, and avoid becoming extra work for either the API provider or the API consumer.
