Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

Checkpoint: File edits

rUv6a765f68c33a
diff --git a/CLAUDE.md b/CLAUDE.md
index 0a33c8b6ec..bc8960fcc1 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -17,16 +17,45 @@
**MCP alone does NOT execute work - Task tool agents do the actual work!**
+### 🛡️ Anti-Drift Coding Swarm (PREFERRED DEFAULT)
+
+**To prevent goal drift, context drift, and agent desynchronization, ALWAYS use this configuration for coding swarms:**
+
+```javascript
+mcp__ruv-swarm__swarm_init({
+ topology: "hierarchical", // Single coordinator enforces alignment
+ maxAgents: 8, // Smaller team = less drift surface
+ strategy: "specialized" // Clear roles reduce ambiguity
+})
+```
+
+**Why This Prevents Drift:**
+| Choice | Anti-Drift Benefit |
+|--------|-------------------|
+| **hierarchical** | Coordinator validates each output against goal, catches divergence early |
+| **maxAgents: 6-8** | Fewer agents = less coordination overhead, easier alignment |
+| **specialized** | Clear boundaries - each agent knows exactly what to do, no overlap |
+
+**Consensus for Hive-Mind:** Use `raft` (leader maintains authoritative state)
+
+**Additional Anti-Drift Measures:**
+- Frequent checkpoints via `post-task` hooks
+- Shared memory namespace for all agents
+- Short task cycles with verification gates
+
+---
+
### 🔄 Auto-Start Swarm Protocol
When the user requests a complex task (multi-file changes, feature implementation, refactoring), **immediately execute this pattern in a SINGLE message:**
```javascript
// STEP 1: Initialize swarm coordination via MCP (in parallel with agent spawning)
-mcp__claude-flow__swarm_init({
+// USE ANTI-DRIFT CONFIG: hierarchical + specialized + small team
+mcp__ruv-swarm__swarm_init({
topology: "hierarchical",
- maxAgents: 15,
- strategy: "adaptive"
+ maxAgents: 8,
+ strategy: "specialized"
})
// STEP 2: Spawn agents concurrently using Claude Code's Task tool
diff --git a/v3/package-lock.json b/v3/package-lock.json
index da2848703c..b186bc2210 100644
--- a/v3/package-lock.json
+++ b/v3/package-lock.json
@@ -1177,11 +1177,11 @@
}
},
"claude-flow": {
- "version": "3.0.0-alpha.28",
+ "version": "3.0.0-alpha.29",
"license": "MIT",
"dependencies": {
"@claude-flow/aidefence": "^3.0.2",
- "@claude-flow/cli": "^3.0.0-alpha.68",
+ "@claude-flow/cli": "^3.0.0-alpha.69",
"@claude-flow/embeddings": "^3.0.0-alpha.1",
"@claude-flow/hooks": "^3.0.0-alpha.2",
"@claude-flow/mcp": "^3.0.0-alpha.1",