sleepless-agent and auto-company

sleepless-agent
70
Verified
auto-company
44
Emerging
Maintenance 13/25
Adoption 14/25
Maturity 22/25
Community 21/25
Maintenance 10/25
Adoption 10/25
Maturity 3/25
Community 21/25
Stars: 810
Forks: 112
Downloads: 35
Commits (30d): 11
Language: Python
License: MIT
Stars: 119
Forks: 44
Downloads:
Commits (30d): 0
Language: Python
License:
No risk flags
No License No Package No Dependents

About sleepless-agent

context-machine-lab/sleepless-agent

🤖 24/7 AI agent that maximizes Claude Code Pro usage via Slack. Auto-processes tasks, manages isolated workspaces, creates Git commits/PRs, and optimizes day/night usage thresholds.

Leverages the Claude Code Python Agent SDK and CLI to execute tasks in isolated workspaces with full file system access, while maintaining a SQLite-backed task queue for persistent management. Integrates with Slack via Socket Mode for asynchronous command handling and supports interactive chat sessions in dedicated threads where Claude can read/write project files in real-time. Automates Git workflows—creating feature branches, commits, and pull requests—while tracking Claude Code Pro usage quotas to optimize execution across configurable day/night time windows.

About auto-company

nicepkg/auto-company

🤖 A fully autonomous AI company that runs 24/7. 14 AI agents (Bezos, Munger, DHH...) brainstorm ideas, write code, deploy products & make money — no human in the loop. Powered by Claude Code.

Orchestrates multi-agent decision-making through persistent state in `memories/consensus.md`, with each autonomous cycle (30-second intervals by default) invoking Claude Code to execute specialized workflows across 14 domain-expert personas. Implements hard safety guardrails in `CLAUDE.md` (credential protection, repository deletion prevention) and uses convergence rules to force execution over discussion—brainstorm → validation → ship, with pre-mortem analysis and market verification gates between ideation and deployment.

Scores updated daily from GitHub, PyPI, and npm data. How scores work