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

fix(mcp): sharpen high-overlap tool descriptions for better selection (#1748 Issue 4) (v3.6.30) (#1756)

rUvcc114c8db463
diff --git a/package.json b/package.json
index e1587fb121..9121bef33d 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
{
"name": "claude-flow",
- "version": "3.6.29",
+ "version": "3.6.30",
"description": "Ruflo - Enterprise AI agent orchestration for Claude Code. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration",
"main": "dist/index.js",
"type": "module",
diff --git a/ruflo/package.json b/ruflo/package.json
index 71dd0702d1..86d6e66d98 100644
--- a/ruflo/package.json
+++ b/ruflo/package.json
@@ -1,6 +1,6 @@
{
"name": "ruflo",
- "version": "3.6.29",
+ "version": "3.6.30",
"description": "Ruflo - Enterprise AI agent orchestration platform. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration",
"main": "bin/ruflo.js",
"type": "module",
diff --git a/v3/@claude-flow/cli/package.json b/v3/@claude-flow/cli/package.json
index faac07a378..42d14b02b0 100644
--- a/v3/@claude-flow/cli/package.json
+++ b/v3/@claude-flow/cli/package.json
@@ -1,6 +1,6 @@
{
"name": "@claude-flow/cli",
- "version": "3.6.29",
+ "version": "3.6.30",
"type": "module",
"description": "Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code",
"main": "dist/src/index.js",
diff --git a/v3/@claude-flow/cli/src/mcp-tools/agent-tools.ts b/v3/@claude-flow/cli/src/mcp-tools/agent-tools.ts
index c16d0d45dc..8ff038cced 100644
--- a/v3/@claude-flow/cli/src/mcp-tools/agent-tools.ts
+++ b/v3/@claude-flow/cli/src/mcp-tools/agent-tools.ts
@@ -180,7 +180,7 @@ async function determineAgentModel(
export const agentTools: MCPTool[] = [
{
name: 'agent_spawn',
- description: 'Spawn a new agent with intelligent model selection',
+ description: 'Spawn a Ruflo-tracked agent with cost attribution + memory persistence + swarm coordination. Use when native Task tool is wrong because you need (a) cost tracking per agent in the cost-tracking namespace, (b) cross-session learning via the patterns namespace, or (c) coordination with other agents in a swarm topology (hierarchical / mesh / consensus). For one-shot subtasks with no learning loop, native Task is fine. Pair with hooks_route to pick the right model first.',
category: 'agent',
inputSchema: {
type: 'object',
diff --git a/v3/@claude-flow/cli/src/mcp-tools/hooks-tools.ts b/v3/@claude-flow/cli/src/mcp-tools/hooks-tools.ts
index e3de24ea5b..647dce1c11 100644
--- a/v3/@claude-flow/cli/src/mcp-tools/hooks-tools.ts
+++ b/v3/@claude-flow/cli/src/mcp-tools/hooks-tools.ts
@@ -882,7 +882,7 @@ export const hooksPostCommand: MCPTool = {
export const hooksRoute: MCPTool = {
name: 'hooks_route',
- description: 'Route task to optimal agent using semantic similarity (native HNSW or pure JS)',
+ description: 'Get a 3-tier routing recommendation for a task: Tier 1 (Agent Booster, 0ms / $0 β€” for var-to-const, add-types, etc.), Tier 2 (Haiku β€” simple), Tier 3 (Sonnet/Opus β€” complex). Use this BEFORE spawning an agent to avoid sending simple transforms to Sonnet. Native tools have no equivalent β€” Claude Code does not introspect its own model-selection cost. Returns the recommended model + a `[AGENT_BOOSTER_AVAILABLE]` literal when the WASM bypass applies.',
inputSchema: {
type: 'object',
properties: {
diff --git a/v3/@claude-flow/cli/src/mcp-tools/memory-tools.ts b/v3/@claude-flow/cli/src/mcp-tools/memory-tools.ts
index 54b7172576..669672d1ea 100644
--- a/v3/@claude-flow/cli/src/mcp-tools/memory-tools.ts
+++ b/v3/@claude-flow/cli/src/mcp-tools/memory-tools.ts
@@ -192,7 +192,7 @@ async function ensureInitialized(): Promise<void> {
export const memoryTools: MCPTool[] = [
{
name: 'memory_store',
- description: 'Store a value in memory with vector embedding for semantic search (sql.js + HNSW backend). Use upsert=true to update existing keys.',
+ description: 'Persistent key-value store with vector embedding β€” survives across sessions and is searchable by meaning, not just by file path. Use when native Write is wrong because the data is not a file (e.g. a learned pattern, a decision, a budget config) AND you need to recall it later by semantic query, not by path. Defaults to namespace="default"; pass --upsert=true to update an existing key.',
category: 'memory',
inputSchema: {
type: 'object',
@@ -272,7 +272,7 @@ export const memoryTools: MCPTool[] = [
},
{
name: 'memory_retrieve',
- description: 'Retrieve a value from memory by key',
+ description: 'Read back a value previously stored via memory_store, by exact (namespace, key) β€” lossless, includes metadata. Use when native Read is wrong because the value is not a file (it lives in the .swarm/memory.db SQLite store) AND you know the exact key. For semantic lookup by meaning, use memory_search.',
category: 'memory',
inputSchema: {
type: 'object',
@@ -336,7 +336,7 @@ export const memoryTools: MCPTool[] = [
},
{
name: 'memory_search',
- description: 'Semantic vector search using HNSW index (150x-12,500x faster than keyword search)',
+ description: 'Find stored memories by meaning (vector similarity), not by literal text β€” finds "JWT auth pattern" when you query "token-based login flow". Use when native Grep is wrong because Grep matches characters and you need to find conceptually-related entries across past sessions. Backed by HNSW index over ONNX embeddings; returns top-k with similarity scores. Pair with smart=true for query expansion + MMR diversity.',
category: 'memory',
inputSchema: {
type: 'object',
@@ -462,7 +462,7 @@ export const memoryTools: MCPTool[] = [
},
{
name: 'memory_delete',
- description: 'Delete a memory entry by key',
+ description: 'Remove a stored memory entry by exact (namespace, key). Use when a previously stored decision is invalidated or contains stale data. No native equivalent β€” Write to a file does not affect the .swarm/memory.db SQLite store.',
category: 'memory',
inputSchema: {
type: 'object',
@@ -505,7 +505,7 @@ export const memoryTools: MCPTool[] = [
},
{
name: 'memory_list',
- description: 'List memory entries with optional filtering',
+ description: 'Enumerate stored memory entries (optionally filtered by namespace/tags) without semantic search. Use when native Glob is wrong because the entries are not files (they live in .swarm/memory.db). For inspection / audit / "what is in my memory" β€” pair with memory_search for retrieval-by-meaning.',
category: 'memory',
inputSchema: {
type: 'object',