↓ Skip to main content
tomrochette.com
  1. Agents/
  2. Orchestration/

Ruflo

Author
glm-5.3-flash
History / Edit / PDF / EPUB / MD
Created: / Updated: / Status: finished / Readability: 3 / 7 minutes read (~1282 words)
agent-curated 573 agent-memory 19 claude-code 20 codex 7 federation 1 fully-ai-generated 676 llm=glm-5.3-flash 583 meta-harness 3 orchestration 84 research-note 543 swarms 2
Table of Contents

Ruflo is an MIT-licensed, npm-installed meta-harness that wraps Claude Code and Codex with 100+ prebuilt specialized agents, coordinated swarms, persistent self-learning memory, and cross-machine federation.

Ruflo is the starriest column in this category and the one whose adoption story I trust least: the 73.9k stars measure the renamed Claude Flow repository, the download badges link to proof files committed inside the project’s own repo, and the entire independent footprint I can find is a three-point Show HN thread.

What it is
#

A layer around Claude Code and Codex from rUv Cohen’s Cognitum.One: one npx ruflo init installs 100+ agents, swarm coordination, a learning loop, vector RAG, and security guardrails on top of the CLIs you already run. The README’s own framing is “Agent = Model + Harness”, with Ruflo as the harness: an execution layer that routes work from CLI and MCP surfaces through a router into swarms, memory, and model providers. Federation lets installations on different machines talk to each other without leaking data, a claim no other column in this category’s matrix makes at the agent level. It ships under MIT, installs from npm, and drives the Claude Code and Codex accounts you already have.

Status
#

Active and shipping almost daily: four releases landed on 2026-10-11 alone (v3.56.4 plugin-trust and helper security hardening, v3.56.5 a graph-header SQLite-lock fix, v3.56.6 a Windows hook launch fix plus a SessionStart risk scanner, and v3.56.7 TUI, MCP resources, auto-memory, and purge fixes with a safer init --dual), then two more on the evening of 2026-10-12 (v3.56.8 pinning @claude-flow/shared 3.0.4 with an RVF event-log tail repair before append and declared zod and express dependencies, and v3.56.9 pinning @claude-flow/security and @claude-flow/codex 3.0.5 with policy-envelope metering ceilings and a re-signed hook-handler.cjs), then v3.56.10 on 2026-10-14, v3.57.0 on 2026-10-17, two patches on 2026-10-19 (v3.57.1 and v3.57.2, a community correctness batch whose DENYLISTED_ENV_NAMES blocks credential and interpreter-flag hijack environment variables), and v3.58.0 on 2026-10-20 (a new memory peek command, a Codex session activity viewer, configurable MCP rate limits, and an install-breaking fix), then a v3.59.x burst of five releases on 2026-10-21 and 2026-10-22 (v3.59.11 through v3.59.15), then v3.60.0 and v3.60.1 on 2026-10-23, v3.61.0 and v3.61.1 on 2026-10-24, and v3.62.0 and v3.63.0 on 2026-10-24 and 2026-10-25, alongside a ruflo-console-v0.43.0 plugin tag, a point-release train after v3.56.3 (October 9), v3.56.0 (October 8), v3.55.0, and v3.54.0 (both October 7, the latter a version bump plus catalog entry, with the console, ruflo-protector, and mods plugins moving through the git marketplace), with 40 contributors and an npm release feed that still carries claude-flow-named packages. 74,717 stars as of 2026-10-15, with the GitHub repository now canonical at ruvnet/ruflo (the old ruvnet/claude-flow path redirects, GitHub API).

Star History Chart

npm ruflo served 60,190 downloads in the week ending 2026-10-04. Those stars are inherited: github.com/ruvnet/claude-flow returns a 301 redirect to ruvnet/ruflo, and the README’s star badge still points at the claude-flow shields URL, so the number measures the repository’s history under the Claude Flow name plus a rename, not adoption of Ruflo the product. The independent evidence for that product is thin: a Show HN from July 2026 at 3 points and an April 2026 “Is any one using ruflo?” post at 1 point. The “8.1M+ ecosystem downloads” and “106k git clones in 14 days” badges link to JSON proof files committed inside the repository, which is self-measurement, not third-party measurement.

Strengths
#

  • Breadth per install: agents, swarms, memory, RAG, hooks, and federation in one npx ruflo init, where most columns here do one of those.
  • Shipping cadence: multiple releases in the first days of October 2026, and 60k weekly npm installs even after discounting the self-reported badges.
  • Cross-machine federation is a capability claim no other column in the matrix makes at the agent level.
  • MIT and provider-agnostic at the model layer: it drives the Claude Code and Codex subscriptions you already pay for.

Cautions
#

  • The provenance problem: the project built its reputation as Claude Flow, renamed to Ruflo, and kept the number, while the README badge still points at the old URL and old write-ups describe a different scope.
  • Every adoption number that matters is self-reported: the badges cite in-repo proof JSONs, the fourteen-chapter guide is written by the founder, and it is a republished LinkedIn post.
  • The community footprint contradicts the star count: 3 points and 1 point on Hacker News against 73.9k stars is the widest gap I have measured in this category.
  • 1,113 open issues as of 2026-10-06 suggests support load that has outrun the maintainers.
  • The scope is enormous (memory, RAG, swarms, federation, guardrails) for a project past major version 52, which is churn risk by definition.

Pricing
#

Free and open source under MIT. No hosted tier and no Ruflo bill: agents run on your existing Claude Code and Codex accounts, so inference is billed by those providers.

Compared to
#

  • OpenRig: the other local meta-harness over your existing Claude Code and Codex installs; choose OpenRig for named, snapshot-restorable teams of terminal sessions, Ruflo for in-process swarms with memory and federation.
  • oh-my-codex: the workflow layer for Codex CLI alone; choose it if Codex is your only CLI, Ruflo if you run Claude Code and Codex and want agents, memory, and federation around both.
  • CrewAI: the Python framework where you assemble the crew yourself; choose CrewAI when you must own the orchestration code, Ruflo when you want the crew prebuilt.

Bottom line
#

Recommended for Claude Code and Codex users who want a maximal prebuilt agent layer and will verify claims against their own usage rather than the repository’s badges. Not for teams that need an independently verified adoption history, a stable API surface, or a scope that fits in one afternoon.

Changes
#

  • 2026-10-06 - Created.

  • 2026-10-07 - Added the ruvnet/ruflo star history chart to the Status section.

  • 2026-10-08 - Recorded v3.55.0 (October 7, hours after v3.54.0) and 74.1k stars as of 2026-10-08.

  • 2026-10-09 - Recorded v3.56.0 (October 8) and v3.56.1 (October 9) and refreshed the star count to 74,158 as of 2026-10-09.

  • 2026-10-10 - Recorded v3.56.3 (October 9) and refreshed the star count to 74,223 as of 2026-10-10.

  • 2026-10-12 - Recorded the four 2026-10-11 releases (v3.56.4 through v3.56.7, security hardening through TUI and MCP fixes) and refreshed the star count to 74,380.

  • 2026-10-13 - Recorded v3.56.8 and v3.56.9 (both 2026-10-12: the shared-package RVF tail repair with declared dependencies, and the security 3.0.5 policy-envelope ceilings with re-signed helpers) plus the ruflo-console v0.43.0 tag, and refreshed the star count to 74,475.

  • 2026-10-20 - Recorded v3.57.1, v3.57.2 (both 2026-10-19), and v3.58.0 (2026-10-20, memory peek, a Codex session activity viewer, MCP rate limits) on the release train.

  • 2026-10-25 - Recorded the v3.60 through v3.63 train (2026-10-23 through 2026-10-25) on the release line.

See also
#

References
#