moflo
Active·★ 19·MIT·Updated 2026-10-21
MoFlo is an opinionated AI agent orchestration toolkit designed specifically for Claude Code, enhancing its capabilities with features like semantic memory, automated indexing, and learned routing. It runs entirely locally, requiring no external services or API keys, and continuously learns and improves from your coding sessions.
#AI Agent Orchestration#Claude Code Integration#Local Development#Semantic Memory#Vector Search#Automated Indexing#Task Automation
01
Features
01Semantic Memory: Utilizes 384-dim domain-aware embeddings to store and instantly search project knowledge.
02Learned Routing: Routes tasks to the optimal agent type, continuously improving efficiency by learning from task outcomes.
03Automated Indexing: Automatically indexes guidance documentation, code structure, and test files at the start of each session.
04Gate System: Enforces memory-first and task-creation patterns via Claude Code hooks, preventing blind exploration and ensuring structured agent use.
05Spells Engine: Allows defining multi-step automations as declarative YAML, supporting complex workflows with shell commands, agent spawns, and flow control.
02
Compatibility
Node.js
Runtime
Verified via docs
Claude Code
AI Client
Verified via docs
macOS
OS
Verified via docs
Linux
OS
Verified via docs
Windows
OS
Verified via docs
GitHub
Integration
Verified via docs
03
Quick start
1
$ npm install --save-dev moflo
2
$ flo init
04
Use cases
↳Improving Claude Code's project understanding and knowledge retention across sessions without manual configuration.
↳Automating multi-step development workflows and repetitive tasks (e.g., lint, test, deploy) using declarative spells with sandboxing.
↳Executing GitHub issues end-to-end, covering research, implementation, testing, and pull request creation.
↳Auditing project setup and guiding Claude with project-specific documentation and best practices via the `/eldar` skill.
↳Sharing learned knowledge and durable patterns across different Git worktrees or team members for collective intelligence.
05
Alternatives
omk★ 148
Evidence-gated runner for Codex, Claude Code, OpenCode, and local coding agents. Routes tasks into scoped DAG lanes with replayable artifacts.
agentic-kit★ 61
One command to install, heal & prove ruflo (claude-flow) + agentic-qe — plus Claude + Codex dual-host with per-activity model routing. Thin, reversible, cross-platform.
nora★ 59
Self-hosted control plane to deploy, monitor, and operate OpenClaw and Hermes AI agents on Docker/Kubernetes — with REST, CLI, and MCP.
murmur★ 20
Murmur — encrypted agent-to-agent messaging bus for AI coding agents. MCP-native, E2E encrypted (XChaCha20-Poly1305), NATS transport with optional JetStream durability, cross-host and cross-org federation + A2A interop. Connect Claude Code, Codex and friends across machines.
trinity★ 691
Self-hosted AI Agents Platform supporting Claude Code, Codex, Gemini agents. Apache 2.0.
claude-vibe-squad★ 164
Multi-model AI orchestration where behaviour is Markdown, not code. One coordinator routes scoped task packets to 71 role-based specialists across 5 model families (Codex / Claude / Gemini / Grok / Kimi) — each working in an isolated git worktree, each reviewed by a rival family before it lands. One tmux session, no server.
Comments
Log in to leave a comment
No comments yet. Be the first!