MoFlo

An opinionated fork of Ruflo/Claude Flow, optimized for local development.

TL;DR

MoFlo makes your AI coding assistant remember what it learns, check what it knows before exploring files, and get smarter over time — all automatically. Install it, run flo init, restart your AI client, and everything just works: your docs and code are indexed on session start so the AI can search them instantly, gates prevent the AI from wasting tokens on blind exploration, task outcomes feed back into routing so it picks the right agent type next time, and context depletion warnings tell you when to start a fresh session. No configuration, no API keys, no cloud services — it all runs locally on your machine.

Quickstart

npm install --save-dev moflo
flo init

Restart Claude Code (or your MCP client). That's it — memory, indexing, gates, and routing are all active.

Or — just ask Claude to install MoFlo into your project and initialize it!

To verify everything is running, ask Claude to run flo doctor with full diagnostics after restarting. If anything fails, ask Claude to fix it with flo doctor --fix.

Opinionated Defaults

MoFlo makes deliberate choices so you don't have to:

• Fully self-contained — No external services, no cloud dependencies, no API keys. Everything runs locally on your machine.
• Minimal dependencies — small runtime dep set (fastembed for embeddings, plus js-yaml, semver, sql.js, valibot). The upstream Ruflo/Claude Flow packages pull in multiple internal scoped packages (@claude-flow/cli, @claude-flow/mcp, @claude-flow/shared) plus native crypto libraries. MoFlo consolidates everything into a single package with no native compilation on install — fastembed's onnxruntime-node ships prebuilt binaries, and sql.js is WASM.
• Node.js runtime — Targets Node.js specifically. All scripts, hooks, and tooling are JavaScript/TypeScript. No Python, no Rust binaries, no native compilation.
• sql.js (WASM) — The memory database uses sql.js, a pure WebAssembly build of SQLite. No native better-sqlite3 bindings to compile, no platform-specific build steps. Works identically on Windows, macOS, and Linux.
• Neural embeddings by default — 384-dimensional embeddings via fastembed (Qdrant's embeddings-only ONNX client) with all-MiniLM-L6-v2. No hash fallback, no peer-optional setup, no install prompts — real semantic search works out of the box. Install footprint: ~60–100 MB post-prune (a postinstall script trims onnxruntime-node to the current platform's binaries and strips GPU-only provider libraries that fastembed never loads; unpruned it would be ~430 MB on Linux). The prune is scoped to ORT copies moflo actually owns and never touches foreign installs (e.g. an Electron cross-compile packager pulling its own ORT); set MOFLO_NO_PRUNE=1 to disable pruning entirely, or ONNXRUNTIME_NODE_INSTALL_CUDA=true to keep the prune but re-enable the CUDA GPU provider. For context, the upstream Ruflo default install is ~1.1 GB. See ADR-EMB-001.
• Full learning stack wired up OOTB — The following are all configured and functional from flo init, no manual setup:
  • SONA (Self-Optimizing Neural Architecture) — learns from task trajectories via pure TypeScript SONA implementation in src/cli/neural/
  • MicroLoRA — rank-2 LoRA weight adaptations at ~1µs per adapt via pure TypeScript MicroLoRA in src/cli/neural/
  • EWC++ (Elastic Weight Consolidation) — prevents catastrophic forgetting across sessions
  • HNSW Vector Search — fast nearest-neighbor search via HNSW indexing with sql.js (WASM SQLite)
  • Semantic Routing — maps tasks to agents via learned routing in cli/src/hooks (ReasoningBank)
  • Trajectory Persistence — outcomes stored in routing-outcomes.json, survive across sessions
  • All pure TypeScript/WASM-based, no GPU, no API keys, no external services.
• Memory-first — Claude must search what it already knows before exploring files. Enforced by hooks, not just instructions.
• Task registration before agents — Sub-agents can't spawn until work is tracked. Prevents runaway agent proliferation.
• Learned routing — Task outcomes feed back into the routing system automatically. No manual configuration needed — it gets smarter with use.
• Incremental indexing — Guidance and code map indexes run on every session start but skip unchanged files. Fast after the first run.
• Built for Claude Code, works with others — We develop and test exclusively with Claude Code. The MCP tools, memory system, and hooks are client-independent and should work with any MCP-capable AI client, but Claude Code is the only tested target.
• GitHub-oriented — The /flo skill, PR automation, and issue tracking are built around GitHub. With Claude's help, you can adapt them to your own issue tracker and source control system.
• Cross-platform — Forward-slash path normalization, no sh -c shell commands, windowsHide on all spawn calls.

Features

Getting Started

1. Install and init

npm install --save-dev moflo
flo init

flo init automatically scans your project to find where your guidance, code, and tests live, then writes the results into moflo.yaml. It looks for:

It also generates:

In interactive mode (flo init without --yes), it shows what it found and lets you confirm or adjust before writing.

Migrating from Claude Flow / Ruflo

If flo init detects an existing .claude/settings.json or .claude-flow/ directory (from a prior Claude Flow or Ruflo installation), it treats the project as already initialized and runs in update mode — merging MoFlo's hooks and configuration into your existing setup without overwriting your data. Specifically:

• Hooks — If your .claude/settings.json already has MoFlo-style gate hooks (flo gate), the hooks step is skipped. Otherwise, MoFlo's hooks are written into the file (existing non-MoFlo hooks are not removed).
• MCP servers — MoFlo registers itself as the moflo server in .mcp.json. If you had claude-flow or ruflo MCP servers configured previously, those entries remain untouched — you can remove them manually once you've verified MoFlo is working. The flo doctor command checks for the moflo server specifically.
• Config files — moflo.yaml, CLAUDE.md, and .claude/skills/flo/ follow the same skip-if-exists logic. Use --force to regenerate them.

To force a clean re-initialization over an existing setup:

flo init --force

2. Review your guidance and code settings

Open moflo.yaml to see what init detected. The two key sections:

Guidance — documentation that helps Claude understand your project (conventions, architecture, domain context):

guidance:
  directories:
    - .claude/guidance    # project rules, patterns, conventions
    - docs                # general documentation

Code map — source files to index for "where does X live?" navigation:

code_map:
  directories:
    - src                 # your source code
    - packages            # shared packages (monorepo)
  extensions: [".ts", ".tsx"]
  exclude: [node_modules, dist, .next, coverage]

Tests — test files to index for "what tests cover X?" reverse mapping:

tests:
  directories:
    - tests               # your test files
    - __tests__            # jest-style test dirs
  patterns: ["*.test.*", "*.spec.*", "*.test-*"]
  extensions: [".ts", ".tsx", ".js", ".jsx"]
  exclude: [node_modules, coverage, dist]
  namespace: tests

MoFlo chunks your guidance files into semantic embeddings, indexes your code structure, and maps test files back to their source targets — so Claude searches your knowledge base before touching any files. Adjust these directories to match your project:

# Monorepo with shared docs
guidance:
  directories: [.claude/guidance, docs, packages/shared/docs]
code_map:
  directories: [packages, apps, libs]

# Backend + frontend
code_map:
  directories: [server/src, client/src]

3. Index and verify

flo memory index-guidance    # Index your guidance docs
flo memory code-map          # Index your code structure
flo doctor                   # Verify everything works

Both indexes run automatically at session start after this, so you only need to run them manually on first setup or after major structural changes. The first index may take a minute or two on large codebases (1,000+ files) but runs in the background — you can start working immediately. Subsequent indexes are incremental and typically finish in under a second. To reindex everything at once:

flo memory refresh           # Reindex all content, rebuild embeddings, cleanup, vacuum

Auto-Indexing

MoFlo automatically indexes three types of content on every session start, so your AI assistant always has up-to-date knowledge without manual intervention.

What gets indexed

How it works

1. Session start hook — When your AI client starts a new session, MoFlo's SessionStart hook launches the indexers sequentially in a single background process. This runs silently — you can start working immediately.
2. Incremental — Each indexer tracks file modification times. Only files that changed since the last index run are re-processed. The first run on a large codebase may take a minute or two; subsequent runs typically finish in under a second.
3. Embedding generation — Guidance chunks are embedded using MiniLM-L6-v2 (384 dimensions, WASM). These vectors are stored in the SQLite memory database and used for semantic search.
4. No blocking — The indexers run in the background and don't block your session from starting. You can begin working immediately.

Configuration

Each indexer can be toggled independently in moflo.yaml:

auto_index:
  guidance: true     # Index docs on session start
  code_map: true     # Index code structure on session start
  tests: true        # Index test files on session start

Set any to false to disable that indexer. The underlying data remains in memory — you just stop refreshing it automatically. You can still run indexers manually:

flo memory index-guidance    # Manual guidance reindex
flo memory code-map          # Manual code map reindex
flo memory refresh           # Reindex everything + rebuild embeddings + vacuum

Why this matters

Without auto-indexing, your AI assistant starts every session with a blank slate — it doesn't know what documentation exists, where code lives, or what tests cover which files. It resorts to Glob/Grep exploration, which burns tokens and context window on rediscovery.

With auto-indexing, the AI can search semantically ("how does auth work?") and get relevant documentation chunks ranked by similarity, or ask "where is the user model defined?" and get a direct answer from the code map — all without touching the filesystem.

The Gate System

MoFlo installs Claude Code hooks that run on every tool call. Together, these gates create a feedback loop that prevents Claude from wasting tokens on blind exploration and ensures it builds on prior knowledge.

Gates explained

Smart classification

The memory-first gate doesn't blindly block every request. It classifies each prompt:

• Simple directives (e.g., "commit", "yes", "continue", "looks good") — skip the gate entirely, no memory search required
• Task-oriented prompts (e.g., "fix the auth bug", "add pagination to the API") — gate enforced, must search memory first

Escape hatch

Prefix any prompt with @@ to bypass the memory-first gate for that turn. Useful for conversational questions, thinking out loud, or discussions that don't need prior context:

@@ what do you think about this approach?
@@ question — is there a better way to handle auth tokens?

The @@ prefix is stripped before Claude sees the prompt, so it won't affect the response.

Disabling gates

All gates are configurable in moflo.yaml:

gates:
  memory_first: true          # Set to false to disable memory-first enforcement
  task_create_first: true     # Set to false to disable TaskCreate enforcement
  context_tracking: true      # Set to false to disable context bracket warnings

You can also disable individual hooks in .claude/settings.json by removing the corresponding hook entries.

The /flo Skill

Inside your AI client, the /flo (or /fl) slash command drives GitHub issue execution:

/flo <issue>                  # Full process (research → implement → test → PR)
/flo -t <issue>               # Ticket only (research and update ticket, then stop)
/flo -r <issue>               # Research only (analyze issue, output findings)
/flo -s <issue>               # Swarm mode (multi-agent coordination)
/flo -h <issue>               # Hive-mind mode (consensus-based coordination)
/flo -n <issue>               # Normal mode (default, single agent, no swarm)

For full options and details, type /flo with no arguments — your AI client will display the complete skill documentation. Also available as /fl.

Epic handling

When you pass an issue number, /flo automatically checks if it's an epic — no extra flag needed. An issue is treated as an epic if any of these are true:

• It has a label matching epic, tracking, parent, or umbrella (case-insensitive)
• Its body contains a ## Stories or ## Tasks section
• Its body has checklist-linked issues: - [ ] #101
• Its body has numbered issue references: 1. #101
• The issue has GitHub sub-issues (via the API)

When an epic is detected, /flo processes each child story sequentially — full process per story (research → implement → test → PR), one at a time, in the order listed.

For simple epics with independent stories, /flo <epic> is all you need. For complex features where you want state tracking, resume capability, and auto-merge between stories, use flo epic instead.

Feature Orchestration (flo epic)

flo epic is the robust epic runner — it adds persistent state, resume from failure, and auto-merge between stories on top of /flo. It accepts either a GitHub issue number or a YAML file:

# From a GitHub epic (auto-detects stories)
flo epic run 42                        # Fetch epic #42, run all stories sequentially
flo epic run 42 --dry-run              # Preview execution plan without running
flo epic run 42 --no-merge             # Skip auto-merge between stories

# From a YAML definition (explicit dependencies)
flo epic run feature.yaml              # Execute stories in dependency order
flo epic run feature.yaml --dry-run    # Show execution plan
flo epic run feature.yaml --verbose    # Stream Claude output to terminal

# State management
flo epic status epic-42                # Check progress (which stories passed/failed)
flo epic reset epic-42                 # Reset state for re-run

When given an issue number, flo epic fetches the epic from GitHub, extracts child stories from checklists and numbered references, then runs each through /flo with state tracking. If a story fails, you can fix the issue and flo epic run 42 again — it resumes from where it left off, skipping already-passed stories.

For features with inter-story dependencies (story B requires story A to be merged first), use a YAML definition:

feature:
  id: my-feature
  name: "My Feature"
  repository: /path/to/project
  base_branch: main

  stories:
    - id: story-1
      name: "Entity and service"
      issue: 101

    - id: story-2
      name: "Routes and tests"
      issue: 102
      depends_on: [story-1]

Spells

What are spells?

Spells are declarative YAML automations composed of pluggable step commands. They exist because shell scripts drift, ad-hoc prompts aren't reproducible, and CI/CD pipelines are the wrong tool for local automation. A spell is deterministic (same inputs → same steps), reviewable (a YAML file you read like a recipe), and replayable (re-cast it tomorrow and it behaves the same). Spells run from the CLI (flo spell cast), from an MCP tool call inside your AI client, or on a schedule.

How do they work?

Each cast goes through the same lifecycle:

1. Parse & validate — YAML is parsed and every step's config is checked against its command's schema.
2. Resolve capabilities — every step declares what it needs (shell, network, fs:read, fs:write, memory, credentials, browser, agent). Undeclared access is rejected before execution.
3. Execute the step graph — steps run sequentially by default, or in parallel groups, with depends_on for ordering and condition/loop for flow control.
4. Outputs flow forward — any step can reference a prior step's output as {stepId.field}, so later steps can consume earlier results.
5. Persistence — memory writes, artifacts, and per-step logs persist between runs; pause/resume and dry-run are supported.

flo spell cast -n development            # Cast a named spell
flo spell cast -f ./my-spell.yaml        # Cast from a file
flo spell cast -n sa --dry-run           # Validate without casting
flo spell list                           # List available spells and recent runs
flo spell grimoire list                  # Browse built-in spell templates
flo spell schedule list                  # List scheduled spells

Defining spells

name: my-spell
steps:
  - name: lint
    command: npm run lint
  - name: test
    command: npm test
  - name: deploy
    command: ./deploy.sh
    depends_on: [lint, test]

Steps support shell (bash), agent spawns, memory reads/writes, conditionals, loops, parallel groups, HTTP/IMAP/Slack/MCP connectors, and more. See docs/SPELLS.md for the full schema.

Sandboxing and security

Spells run with least-privilege access. Each step command declares the capabilities it needs (shell, net, fs:read, fs:write, memory, credentials, browser, agent), and the runner blocks any undeclared access. Spell authors can further restrict capabilities per step — e.g. fs:read: ["./config/"] or shell: ["cat", "jq"] — but never expand them.

Bash steps also run inside an OS sandbox when one is available. MoFlo auto-selects the best tier installed on your machine:

The sandbox is network-off by default; a step must explicitly declare net to reach the outside world. Credentials referenced as {credentials.X} are resolved from the encrypted credential store, masked in logs, and never written to disk. A destructive-pattern checker refuses to run bash commands that look like rm -rf /, unscoped git push --force, and similar footguns. See docs/SPELL-SANDBOXING.md for the full model.

Reusability

You interact with spells at three tiers:

1. Shipped spells — bundled with MoFlo and ready to cast. Browse them with flo spell grimoire list.
2. User spells — YAML files you drop in .claude/spells/. Override the location in moflo.yaml:

   spells:
     userDirs:
       - .claude/spells
       - my/project/spells
   

   A user spell with the same name as a shipped one wins — that's how you customize a shipped spell without forking.
3. Custom step commands and connectors — drop TypeScript/JavaScript files in .claude/spells/steps/ (new step types) and .claude/spells/connectors/ (new connectors). They're auto-discovered at startup. Connectors that wrap heavy SDKs (IMAP, MCP) declare those SDKs as optionalDependencies; install them only if your spells use them.

Scheduling

Spells can run on a schedule. The MoFlo background daemon polls for due spells once a minute and casts them — no external cron, no extra services.

Three timing options:

# Cron (5 fields: minute hour day-of-month month day-of-week)
flo spell schedule create -n nightly-audit --cron "0 2 * * *"

# Interval (e.g., 90s, 30m, 6h, 1d)
flo spell schedule create -n health-check --interval 30m

# One-time (ISO 8601 datetime)
flo spell schedule create -n migration --at 2026-04-15T09:00:00Z

You can also declare a schedule directly inside the spell YAML — that registers it on every daemon start:

name: nightly-audit
schedule:
  cron: "0 2 * * *"
steps:
  - id: audit
    type: bash
    config:
      command: ./scripts/audit.sh

Daemon prerequisite. Schedules only fire while the daemon is running. To survive reboot:

flo daemon install   # registers an OS-level autostart service
flo daemon status    # shows whether the service is registered AND running

flo spell schedule create warns when the daemon isn't installed so you don't quietly miss runs.

Monitoring. The daemon dashboard surfaces live schedules, recent executions, and per-schedule controls (disable / re-enable / run now). It starts alongside the daemon at http://localhost:3117 (override with --dashboard-port or disable with --no-dashboard).

For full configuration (scheduler: block in moflo.yaml), event types, and the catch-up window after restarts, see docs/SPELLS.md#scheduling.

Building spells with the /spell-builder skill

Inside your AI client, use the /spell-builder skill to create, edit, and validate spell definitions interactively. The skill understands the full spell schema and available step commands, so you can describe what you want in natural language and it will generate the YAML:

/spell-builder                           # Start the spell builder

Epics

Epics are a specialized process for handling GitHub issues that contain multiple child stories. When you pass a GitHub issue to /flo and it's detected as an epic, MoFlo processes each child story sequentially through the full /flo process (research → implement → test → PR).

For simple epics, /flo <epic-number> is all you need. For complex features requiring state tracking, resume from failure, and auto-merge between stories, use the dedicated flo epic command:

flo epic 42                              # Run all stories in epic #42
flo epic 42 --strategy auto-merge        # Per-story PRs with auto-merge
flo epic 42 --dry-run                    # Preview execution plan
flo epic status 42                       # Check progress
flo epic reset 42                        # Reset state for re-run

For features with inter-story dependencies, define them in a YAML file with depends_on fields for topological ordering. See the Epic handling section above for detection criteria and the full comparison between /flo <epic> and flo epic run.

Commands

You don't need to run these for normal use — flo init sets everything up, and the hooks handle memory, routing, and learning automatically. These commands are here for manual setup, debugging, and tweaking.

Memory

flo memory store -k "key" --value "data"    # Store with 384-dim embedding
flo memory search -q "auth patterns"         # Semantic search
flo memory index-guidance                    # Index guidance docs
flo memory code-map                          # Index code structure
flo memory rebuild-index                     # Regenerate all embeddings
flo memory refresh                           # Reindex all + rebuild + cleanup + vacuum
flo memory stats                             # Show statistics

Routing & Learning

flo hooks route --task "description"          # Route task to optimal agent
flo hooks learn --pattern "..." --domain "."  # Store a pattern
flo hooks patterns                            # List learned patterns
flo hooks consolidate                         # Promote/prune patterns

Gates

flo gate check-before-scan       # Blocks Glob/Grep if memory not searched
flo gate check-before-agent      # Blocks Agent tool if no TaskCreate
flo gate prompt-reminder         # Context bracket tracking
flo gate session-reset           # Reset gate state

Diagnostics

flo doctor                       # Quick health check (environment, deps, config)
flo doctor --fix                 # Auto-fix issues (memory DB, daemon, config, MCP, zombies)
flo diagnose                     # Full integration test (memory, swarm, hive, hooks, neural)
flo diagnose --suite memory      # Run only memory tests
flo diagnose --json              # JSON output for CI/automation

flo doctor — Health Check

flo doctor runs 26 parallel health checks against your environment and reports pass/warn/fail for each:

Auto-fix mode (flo doctor --fix) attempts to repair each failing check automatically:

After auto-fixing, doctor re-runs all checks and shows the updated results. Issues that can't be fixed automatically are listed with manual fix commands.

Additional flags:

flo doctor --install             # Auto-install missing Claude Code CLI
flo doctor --kill-zombies        # Find and kill orphaned MoFlo processes
flo doctor -c memory             # Check only a specific component
flo doctor -c embeddings         # Check only embeddings health
flo doctor --verbose             # Verbose output

flo diagnose — Integration Tests

While doctor checks your environment, diagnose exercises every subsystem end-to-end: memory CRUD, embedding generation, semantic search, swarm lifecycle, hive-mind consensus, task management, hooks, config, neural patterns, and init idempotency. All test data is cleaned up after each test — nothing is left behind.

GitHub Repository Setup

flo github setup                  # One-shot: generate CI + apply repo settings + branch protection
flo github setup --dry-run        # Preview everything without making changes
flo github ci                     # Generate .github/workflows/ci.yml from project config
flo github ci --dry-run           # Print CI config to stdout
flo github settings               # Apply repo settings + branch protection via gh CLI
flo github settings --dry-run     # Preview settings changes

flo github ci auto-detects your package manager (npm/pnpm/yarn/bun), TypeScript, and test directories from moflo.yaml and package.json, then generates a GitHub Actions CI pipeline with install, build, lint, type-check, and test steps.

flo github settings applies recommended defaults via gh CLI: delete-branch-on-merge, squash merge with PR title/body, auto-merge, linear history, and configurable branch protection (required reviews, dismiss stale reviews, block force pushes). Requires gh auth login.

System

flo init                          # Initialize project (one-time setup)
flo --version                    # Show version

What Ships Out of the Box

flo init wires up the following systems automatically. Here's what each one does, why it matters, and whether it's enabled by default.

Hooks (enabled OOTB)

Hooks are shell commands that Claude Code runs automatically at specific points in its lifecycle. MoFlo installs 21 hook bindings across 8 lifecycle events. You don't invoke these — they fire automatically.

Systems (enabled OOTB)

These are the backend systems that hooks and commands interact with.

Systems (available but off by default)

The Two-Layer Task System

MoFlo doesn't replace your AI client's task system — it wraps it. Your client (Claude Code, Cursor, or any MCP-capable tool) handles spawning agents and running code. MoFlo adds a coordination layer on top that handles memory, routing, and learning.

┌──────────────────────────────────────────────────┐
│  YOUR AI CLIENT (Execution Layer)                │
│  Spawns agents, runs code, streams output        │
│  TaskCreate → Agent → TaskUpdate → results       │
├──────────────────────────────────────────────────┤
│  MOFLO (Knowledge Layer)                         │
│  Routes tasks, gates agent spawns, stores        │
│  patterns, learns from outcomes                  │
└──────────────────────────────────────────────────┘

Here's how a typical task flows through both layers:

1. MoFlo routes — Before work starts, MoFlo analyzes the prompt and recommends an agent type and model tier via hook or MCP tool.
2. MoFlo gates — Before an agent can spawn, MoFlo verifies that memory was searched and a task was registered. This prevents blind exploration.
3. Your client executes — The actual agent runs through your client's native task system. MoFlo doesn't manage the agent — your client handles execution, output, and completion.
4. MoFlo learns — After the agent finishes, MoFlo records what worked (or didn't) in its memory database. Successful patterns feed into future routing.

The key insight: your client handles execution, MoFlo handles knowledge. Your client is good at spawning agents and running code. MoFlo is good at remembering what happened, routing to the right agent, and ensuring prior knowledge is checked before exploring from scratch.

For complex work, MoFlo structures tasks into waves — a research wave discovers context, then an implementation wave acts on it — with dependencies tracked through both the client's task system and MoFlo's coordination layer. The full integration pattern is documented in .claude/guidance/moflo-claude-swarm-cohesion.md.

The /flo skill ties both systems together for GitHub issues — driving the full process (research → enhance → implement → test → simplify → PR) with your client's agents for execution and MoFlo's memory for continuity.

Intelligent Agent Routing

MoFlo ships with 17 built-in task patterns that map common work to the right agent type:

When you route a task (flo hooks route --task "..." or via MCP), MoFlo runs semantic similarity against these patterns using HNSW vector search and returns a ranked recommendation with confidence scores.

The routing gets smarter over time. Every time a task completes successfully, MoFlo's post-task hook records the outcome — the full task description, which agent handled it, and whether it succeeded. These learned patterns are combined with the built-in seeds on every future route call. Because learned patterns contain rich task descriptions (not just short keywords), they discriminate better as they accumulate.

Routing outcomes are stored in .claude-flow/routing-outcomes.json and persist across sessions. You can inspect them with flo hooks patterns or transfer them between projects with flo hooks transfer.

Memory & Knowledge Storage

MoFlo uses a SQLite database (via sql.js/WASM — no native deps) to store three types of knowledge:

Semantic search uses cosine similarity on neural embeddings (MiniLM-L6-v2, 384 dimensions). When Claude searches memory, it gets the most relevant chunks ranked by semantic similarity — not keyword matching.

Session start indexing — Four background processes run on every session start: the guidance indexer, the code map generator, the test mapper, and the learning service. All four are incremental (unchanged files are skipped) and run in parallel so they don't block the session.

Cross-session persistence — Everything stored in the database survives across sessions. Patterns learned on Monday are available on Friday. The stop hook exports session metrics, and the session-restore hook loads prior state.

For Claude

When flo init runs, it appends a section to your CLAUDE.md that teaches Claude:

• Always search memory before Glob/Grep/Read (enforced by gates)
• Use mcp__moflo__memory_search for knowledge retrieval
• Use /flo <issue> (or /fl) for issue execution
• Store learnings after task completion

Full Configuration Reference

flo init generates a moflo.yaml at your project root. Here's the complete set of options:

project:
  name: "my-project"

guidance:
  directories: [.claude/guidance]
  namespace: guidance

code_map:
  directories: [src, packages]
  extensions: [".ts", ".tsx"]
  exclude: [node_modules, dist]
  namespace: code-map

tests:
  directories: [tests, __tests__]
  patterns: ["*.test.*", "*.spec.*", "*.test-*"]
  extensions: [".ts", ".tsx", ".js", ".jsx"]
  exclude: [node_modules, coverage, dist]
  namespace: tests

gates:
  memory_first: true                 # Must search memory before file exploration
  task_create_first: true            # Must TaskCreate before Agent tool
  context_tracking: true             # Track context window depletion

auto_index:
  guidance: true                     # Auto-index docs on session start
  code_map: true                     # Auto-index code on session start
  tests: true                        # Auto-index test files on session start

mcp:
  tool_defer: true                   # Defer 140+ tool schemas; loaded on demand via ToolSearch
  auto_start: false                  # Auto-start MCP server on session begin

hooks:
  pre_edit: true                     # Track file edits for learning
  post_edit: true                    # Record edit outcomes
  pre_task: true                     # Agent routing before task spawn
  post_task: true                    # Record task results for learning
  gate: true                         # Gate enforcement
  route: true                        # Intelligent task routing
  stop_hook: true                    # Session-end persistence
  session_restore: true              # Restore session state on start

models:
  default: opus
  research: sonnet
  review: opus
  test: sonnet

model_routing:
  enabled: false                     # Set to true for automatic model selection
  confidence_threshold: 0.85
  cost_optimization: true
  circuit_breaker: true

status_line:
  enabled: true
  branding: "MoFlo V4"
  mode: compact                      # single-line, compact, or dashboard
  show_dir: true                      # current directory name (compact/dashboard only)
  show_git: true
  show_session: true
  show_swarm: true
  show_agentdb: true
  show_mcp: true

Tool Deferral

By default, tool_defer is true. MoFlo exposes 140+ MCP tools — loading all their schemas at conversation start consumes significant context. With deferral enabled, only tool names are listed at startup (compact), and full schemas are fetched on demand via ToolSearch when actually needed. Hooks and CLI commands continue to work normally since they call the daemon directly, not through MCP tool schemas.

Set tool_defer: false if you want all tool schemas available immediately (useful for offline/air-gapped environments where ToolSearch may not work).

Model Routing

By default, MoFlo uses static model preferences — each agent role uses the model specified in models:. This is predictable and gives you full control.

Set model_routing.enabled: true to enable intelligent routing, which analyzes each task's complexity and auto-selects the cheapest capable model:

The router learns from outcomes — if a model fails a task, the circuit breaker penalizes it and escalates to a more capable model.

You can pin specific agents even when routing is enabled:

model_routing:
  enabled: true
  agent_overrides:
    security-architect: opus     # Never downgrade security work
    researcher: sonnet           # Pin research to sonnet

Architecture

• 9 bin entries shipped with npm: flo (main CLI), moflo, claude-flow (aliases), flo-setup, flo-codemap, flo-search, flo-embeddings, flo-index, flo-testmap
• Project config system: moflo.yaml for per-project settings
• One-stop init: flo init generates everything needed for OOTB operation

Ruflo / Claude Flow

MoFlo originated as a fork of Ruflo/Claude Flow and has since diverged significantly. The upstream project distributes functionality across multiple scoped packages (@claude-flow/cli, @claude-flow/mcp, @claude-flow/shared) with native crypto dependencies. MoFlo consolidates everything into a single package with 4 runtime dependencies and zero native bindings — the entire stack runs on pure JavaScript/TypeScript and WASM.

For documentation on the underlying capabilities that both projects share — swarm topologies, hive-mind consensus, HNSW vector search, neural routing, MCP server internals — see the Ruflo repository.

Why I Made This

Ruflo/Claude Flow is an incredible piece of work. The engineering that rUv and the contributors have put into it — swarm topologies, hive-mind consensus, HNSW vector search, neural routing, and so much more — makes it one of the most comprehensive agent orchestration frameworks available. It's a massive, versatile toolbox built to support a wide range of scenarios: distributed systems, multi-agent swarms, enterprise orchestration, research workflows, and beyond.

My use case was just one of those many scenarios: day-to-day local coding, enhancing my normal Claude Code experience on a single project. Claude Flow absolutely supports this — it's all in there — but because the project serves so many different needs, I found myself spending time configuring and tailoring things for my specific setup each time I pulled in updates. That's not a shortcoming of the project; it's the natural trade-off of a tool designed to be that flexible and powerful.

So I forked the excellent foundation and narrowed the focus to my particular corner of it. I baked in the defaults I kept setting manually, added automatic indexing and memory gating at session start, and tuned the out-of-box experience so that npm install and flo init gets you straight to coding.

If you're exploring the full breadth of what agent orchestration can do, go use Ruflo/Claude Flow directly — it's the real deal. But if your needs are similar to mine — a focused, opinionated local dev setup that just works — then hopefully MoFlo saves you the same configuration time it saves me.

License

MIT (inherited from Ruflo/Claude Flow)