Daemons
<p> Keep PRs, issues, CI, and docs moving with AI agents </p> <p> <a href="https://www.producthunt.com/products/daemons-by-charlie-labs?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1164563?app_id=339">Link</a> </p>
Last verified:
What is Daemons?
Charlie Labs Daemons are always-on AI processes that work proactively across Slack, Linear, GitHub, and Sentry without requiring explicit prompts or instructions. Daemons are defined using simple Markdown (.md) files that live in your repository, where you specify what the daemon watches, what routines it executes, and what boundaries it cannot cross. The core philosophy is that agents create work while daemons maintain it, making them ideal for teams that have moved past early agent experimentation and are now dealing with operational drag from agent-created output.
Key features include hybrid activation through watch (event-driven from GitHub, Linear, Slack) and schedule (cron-based timed wakes), compound memory that improves with every run, role-based definitions rather than task-based instructions, and predictable autonomy that follows team conventions. Daemons handle organizing (PRs, issues, ownership alignment), maintaining (code, dependencies, docs, runbooks), and following through (turning signals into reviewable PRs, updates, reports, escalations, or fixes). The system supports hybrid activation, rate-limited work per activation, and additive-only operations with deny rules.
Daemons are designed for engineering teams dealing with operational debt, including issue hygiene, docs and dependency maintenance, bug triage, CI repair, and follow-through. They work best in TypeScript and support many common languages/frameworks. The tool is ideal for teams using GitHub, Linear, Slack, and Sentry who want to automate recurring loops like bug triage, dependency updates, PR metadata management, merge conflict repair, and documentation drift maintenance without constant human prompting.
Daemons pricing
Pricing model: Freemium
Free plan at $0 with baseline daily and weekly Charlie usage limits that reset, prepaid overage available above plan limits, supports a few daemons, and unlimited team members. Starter plan at $50/month offers 2.5× Free plan daily and weekly limits, prepaid overage available, unlimited team members, and no max on number of daemons. Team plan at $200/month provides 10× Free plan daily and weekly limits, prepaid overage available, priority Slack support, unlimited team members, and no max on number of daemons. Plans are based on daily/weekly usage limits not monthly credits, you can purchase overage credits to keep running when hitting limits, and plan changes take effect on the next billing cycle. OSS, EDU, and Pre-Seed credits available by contacting [email protected].
Daemons pros
- Works 24/7 without prompts or explicit instruction
- Defined in portable Markdown files in your repo
- Handles operational drag from agent-created output
- Adds once and entire team benefits daily
- No rollout or onboarding required for team
- Compounding memory improves with every run
- Predictable behavior that follows team conventions
- Hybrid activation with watch and schedule
- Supports GitHub, Linear, Slack, and Sentry
- Rate-limited work per activation prevents overwhelm
- Deny rules ensure safe boundary enforcement
- Additive-only operations prevent accidental changes
- Shared token budget for team-based billing
- Open format portable across any supporting provider
- Specialized roles get better over time automatically
Daemons cons
- Not a long-running OS process, only bounded activations
- Strongest in TypeScript, limited other language support
- Cron schedules evaluated only in UTC timezone
- Requires GitHub App installation and OAuth setup
- Linear/Slack event wakes need integration connected
- Usage pauses when hitting plan limits without overage
- No automatic link updating for Linear-GitHub reconciliation
- Complex PRs take longer to review than small ones
Frequently asked questions about Daemons
What does daemon mean in Charlie?
A daemon is a repo-defined operating role for recurring work. It is not a long-running OS process. Each daemon is defined in a file at .agents/daemons/<daemon-id>/DAEMON.md and fulfills an ongoing responsibility with judgment rather than completing a single task.
What is watch vs schedule?
Watch wakes a daemon from matching events like when a pull request is opened or a Linear issue is created. Schedule wakes a daemon on a cron timetable. A daemon can use either one or both for hybrid activation, allowing it to respond to events and sweep periodically.
What wake sources are supported?
Daemons can wake from scheduled cron wakes through schedule, plus routed GitHub, Linear, and Slack events through watch. Linear event wakes require the Linear integration to be connected and the issue's Linear team mapped to the intended repo. Slack event wakes require the Slack integration to be connected and the Slack workspace mapped to the intended repo.
What timezone does daemon cron use?
Cron schedules are evaluated in UTC. All schedule-based daemon activations use UTC timezone regardless of where your team is located.
Are daemon activations bounded?
Yes. Activations are bounded runs with explicit start and end, tool limits, and normal permission constraints. This prevents daemons from running indefinitely and ensures predictable resource usage.
Do daemons keep memory across activations?
Daemons can use prior activation history as context, but they do not run as a permanently active process. They build compound memory that improves with every run, making a daemon at month three sharper than at day one without anyone updating a file.
Which DAEMON.md frontmatter fields are canonical?
Use only the canonical fields: id, purpose, watch, routines, deny, and schedule. Do not invent alternate top-level schema keys for activation mode. The frontmatter between --- fences defines what the daemon is, while Markdown content below defines how it operates.
What languages does Charlie support?
Charlie is strongest in TypeScript and supports many common languages and frameworks used in modern repositories. While TypeScript is the primary strength, the system handles other popular languages found in contemporary development workflows.
How quickly does Charlie review PRs?
Small and medium PRs are typically reviewed in minutes. Complex PRs can take longer when deeper validation is needed, as the system performs more thorough analysis for complicated code changes.
Where do I get support?
Email [email protected] for support. For OSS, EDU, and Pre-Seed credit applications, contact [email protected]. Priority Slack support is available on the Team plan at $200/month.