On-screen text
tests
v3
verification
.gitignore
apmignore
AGENTS.md
CHANGELOG.md
CLAUDE.local.md
CLAUDE.md
LICENSE
README.md
SECURITY.md
agentdb.rvl
feat(adr-857): RVF native storage with securi
doc(readme): add RuFlo Agentic Appliance E
fix(witness): #2021 - refresh stale markers, o
security: untrack .env files + broaden .gitignor
chore(repo): archive legacy v2 / codebase unde
Checkpoint: File edits
feat: RuFlo v3.5.0 - first major stable release
Checkpoint: File edits
feat: lean CLAUDE.md generator with SendM
fix(memory): support namespace in delete conf
doc(readme): add RuFlo Agentic Appliance E
doc(sec): update SECURITY and contact email
feat(mcpl): ADR-112 - 285/285 tool descript
RuFlo
feat(adr-857): RVF native storage with securi
doc(readme): add RuFlo Agentic Appliance E
fix(witness): #2021 - refresh stale markers, o
security: untrack .env files + broaden .gitignor
chore(repo): archive legacy v2 / codebase unde
Checkpoint: File edits
feat: RuFlo v3.5.0 - first major stable release
Checkpoint: File edits
feat: lean CLAUDE.md generator with SendM
fix(memory): support namespace in delete conf
doc(readme): add RuFlo Agentic Appliance E
doc(sec): update SECURITY and contact email
feat(mcpl): ADR-112 - 285/285 tool descript
RuFlo
Platform
Solutions
Resources
Open Source
Enterprise
Pricing
ruvnet/ruflo
ruflo
#8
Full requests
149
Discussions
Projects
Wiki
Security and
Code
plugin
main
288 branches
60+ Specialized Agents
Coordinated swarms with 5 consensus
protocols
Deploy ready-to-use AI agents for coding,
review, testing, security, and DevOps.
Queen-led hierarchy with 8 worker types
(Researcher, Coder, Analyst, Tester,
Architect, Reviewer, Optimizer, Documenter)
using Byzantine fault-tolerant consensus.
README.md
MIT License
Security
What it is
Why it matters
Any model,
local or
remote
6 curated frontier models out-of-the-box: Owen 3.0 Max (default), Claude Sonnet 4.0,
Claude Haiku 4.0, Gemini 2.0 Pro, Gemini 2.5 Flash, Qwen1.5 via OpenRouter. Add your
own: any OpenAl-compatible endpoint (LLM, Claude, Gemini, LLaMA, LLaMA Studio, Together, Groq, self-
hosted).
RuVLLM
self-
learning AI
Native support for ruVLLM (lives in ruvnet/ruvector/examples/ruvl.lk) - RuFlo's self-
improving local model layer. Routes to MicroLLaMA adapters, learns from your trajectories
via SONA, and stays on your machine. Pair with the cloud models or run fully offline.
~210
tools
ready to
call
5 server groups (Core, Intelligence, Agents, Memory, DevTools) plus an 18-tool gallery
that runs entirely in your browser - works offline.
Bring your own
MCP servers
Click the MCP (n) pill in the chat input -> Add Server and paste any MCP endpoint (HTTP,
SSL, or custom). Run your own RuFlo MCP server in the same parallel-execution flow. Run
a local MCP server on total:localhost:3000 and it just works.
Tools run in
parallel
Memory
that sticks
Built-in
capabilities
One model response can fire 4-6+ tools at the same time. The UI then shows them as cards
with a Step 1-2 tools completed badge so you can see exactly what ran.
Say "remember my favorite color is indigo" and ask weeks later - RuFlo recalls it. Backed
by AgentDB + HNSW vector search (150x faster than brute force).
Click the question-mark icon in the sidebar for a "RuFlo Capabilities" mortal agent with
