sudocode
Active·★ 277·Apache-2.0·Updated 2026-03-18
★ Multi-Agent★ Dev Tooling
Lightweight agent orchestration dev tool that lives in your repo
sudocode is a lightweight, git-native agent orchestration system designed to automate context management and enable AI agents to track long-horizon tasks and collaborate effectively. It allows human developers to direct work by organizing requirements, context, and plans into structured issue graphs, reducing the need for constant supervision.
#Agent Orchestration#AI/LLM Development#Git-native#Context Management#Spec-driven Development#Software Development Tools#Human-AI Collaboration#Issue Tracking
01
Features
01Git-native agent memory system for automated context handoff in complex tasks.
02Organize requirements, context, and plans into structured, executable issue graphs.
03Real-time visualization of outputs and execution feedback from agents.
04Dual representation for specs and issues (human-editable Markdown and machine-optimized JSONL/SQLite).
05Integration with popular IDEs (VS Code, Cursor, IntelliJ, etc.) for reviewing agent-generated code.
02
Compatibility
Node.js
Runtime
Verified via docs
Git
Version Control
Verified via docs
AI Agents (LLM Platforms)
Agent Support
Verified via docs
IDEs (VS Code, Cursor, IntelliJ, Zed, Xcode, Windsurf)
IDE Integration
Verified via docs
External Issue/Spec Trackers (Beads, Spec-Kit, OpenSpec)
External Sync
Verified via docs
03
Quick start
1
$ npm install -g sudocode
04
Use cases
↳Automating context and task management for AI agents in software development.
↳Directing AI agent workflows for complex software development projects.
↳Enabling structured human-AI collaboration on coding and planning tasks.
↳Implementing spec-driven development using AI agents to refine and execute requirements.
↳Synchronizing agent memory with external spec and issue tracking systems.
05
Alternatives
ragflow★ 81.5k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
n8n★ 190.2k
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
pal-mcp-server★ 11.6k
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
mcp-memory-service★ 1.9k
Stop re-explaining your project to AI every session. Automatic context memory for Claude, VS Code, Cursor, and 13+ AI tools.
Acontext★ 3.5k
Data platform for context engineering. Context data platform that stores, observes and learns. Join the community❤️: https://discord.acontext.io
Related searches
Comments
Log in to leave a comment
- OOakley DavisMay 13, 2026
Lightweight means low overhead, doesn't slow down your development workflow.
- SSpencer WhiteApr 26, 2026
Repo-resident config makes orchestration behavior reviewable and version-controllable.
- Rowan RiveraApr 25, 2026
Agent orchestration that lives in your repo is the right architecture — config-as-code.
- JJesse DavisMar 17, 2026
Good for teams who want agent coordination without external service dependencies.