codex-swarmOpenAI Codex-native multi-agent swarm orchestration for parallel coding. Use when spawning multiple Codex CLI agents to work in parallel with git worktrees,...
Install via ClawdBot CLI:
clawdbot install linkbag/codex-swarmGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Jul 10, 2026
Multiple builders implement independent features simultaneously using git worktrees and tmux sessions. Each agent works on its own task branch, and the integrator merges them after review.
After all builder agents complete their tasks, the reviewer agent automatically runs code review using 'codex exec review' to ensure code quality before merging.
Use multiple builder agents to refactor different modules in parallel, with the architect coordinating the overall structure and the integrator resolving conflicts.
Architect designs a feature, builders prototype in parallel, and each task must pass an endorsement gate before spawning, ensuring alignment with the overall plan.
After each batch of parallel agents completes and merges, a webhook notifies stakeholders (e.g., Slack/Telegram) about the new integration, enabling fast feedback.
Offer codex-swarm as a service to clients needing fast, parallel feature development. Charge per batch of tasks or per sprint, leveraging the swarm for high throughput.
Deploy within a software company to accelerate development cycles. The tool reduces time-to-market, leading to faster revenue from product releases.
Integrate codex-swarm into a CI/CD platform (e.g., GitHub Actions) and charge per parallel agent usage or per workflow execution.
💬 Integration Tip
Ensure your environment has bash 4+, tmux, git, gh, jq, and the Codex CLI installed. Copy the config/swarm.conf.example to config/swarm.conf and adjust paths.
Scored Jul 10, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...