π 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
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
Checkpoint: File edits
rUvc5019dbc2ac9
diff --git a/v3/implementation/adrs/ADR-STATUS-SUMMARY.md b/v3/implementation/adrs/ADR-STATUS-SUMMARY.mdindex 74db177db0..70ca17550d 100644--- a/v3/implementation/adrs/ADR-STATUS-SUMMARY.md+++ b/v3/implementation/adrs/ADR-STATUS-SUMMARY.md@@ -459,31 +459,43 @@ V3 now implements **171 MCP tools** with full V2 backward compatibility:| **Coordination (V2)** | β Full | β **NEW** | 7 tools || Hooks system | β Full | β Full | 45 tools |-### New V2 Compatibility Tools (alpha.87)--β οΈ **IMPORTANT**: These tools provide **LOCAL STATE MANAGEMENT** for V2 API compatibility.-They do NOT make external API calls or execute real commands. They are useful for:-- Workflow orchestration and coordination-- State tracking across agent sessions-- Local development and testing--| Tool File | Persistence | External API | Notes |-|-----------|-------------|--------------|-------|-| system-tools.ts | β File-based | β None | Illustrative metrics |-| terminal-tools.ts | β File-based | β None | Records commands, doesn't execute |-| github-tools.ts | β File-based | β None | Local state only, no GitHub API |-| neural-tools.ts | β File-based | β None | Simulated training |-| performance-tools.ts | β File-based | Partial | Some real process metrics |-| daa-tools.ts | β File-based | β None | Local agent coordination |-| coordination-tools.ts | β File-based | β None | Local topology state |--**system-tools.ts** (5 tools) - β οΈ Illustrative metrics:-- `system/status` - Get overall system status (simulated)-- `system/metrics` - Get system metrics (illustrative values)+### New V2 Compatibility Tools (alpha.88+)++**Updated 2026-01-13**: V2 tools now use **REAL** capabilities where possible:++| Tool File | Persistence | Real Data | Notes |+|-----------|-------------|-----------|-------|+| system-tools.ts | β File-based | β **REAL** | Real CPU, memory via os/process APIs |+| performance-tools.ts | β File-based | β **REAL** | Real benchmarks with actual timing |+| neural-tools.ts | β File-based | β **REAL** | Real embeddings via @claude-flow/embeddings |+| terminal-tools.ts | β File-based | β State only | Records commands, doesn't execute |+| github-tools.ts | β File-based | β State only | Local state, no GitHub API |+| daa-tools.ts | β File-based | β State only | Local agent coordination |+| coordination-tools.ts | β File-based | β State only | Local topology state |++**system-tools.ts** (5 tools) - β **REAL METRICS**:+- `system/status` - Get overall system status (real health based on metrics)+- `system/metrics` - **REAL**: os.loadavg(), os.cpus(), process.memoryUsage()- `system/health` - Perform system health check- `system/info` - Get system information (real Node.js info)- `system/reset` - Reset system state+**performance-tools.ts** (6 tools) - β **REAL BENCHMARKS**:+- `performance/report` - **REAL**: CPU %, memory MB from process/os APIs+- `performance/bottleneck` - Detect bottlenecks (based on real metrics)+- `performance/benchmark` - **REAL**: Actual timed benchmarks with ops/sec+- `performance/profile` - Profile component (simulated hotspots)+- `performance/optimize` - Apply optimizations (state only)+- `performance/metrics` - **REAL**: CPU/memory with statistics from history++**neural-tools.ts** (6 tools) - β **REAL EMBEDDINGS**:+- `neural/train` - Track training progress (state)+- `neural/predict` - **REAL**: embeddings via @claude-flow/embeddings (agentic-flow)+- `neural/patterns` - **REAL**: Store patterns with real embeddings, cosine similarity search+- `neural/compress` - Compression info (illustrative)+- `neural/status` - **REAL**: Shows embedding provider status+- `neural/optimize` - Optimization suggestions (illustrative)+**terminal-tools.ts** (5 tools) - β οΈ State tracking only:- `terminal/create` - Create a new terminal session record- `terminal/execute` - Record command (does NOT execute - use Bash tool)@@ -491,22 +503,6 @@ They do NOT make external API calls or execute real commands. They are useful fo- `terminal/close` - Close a terminal session record- `terminal/history` - Get command history-**neural-tools.ts** (6 tools) - β οΈ Simulated training:-- `neural/train` - Simulate training a neural model-- `neural/predict` - Make simulated predictions-- `neural/patterns` - Get or manage local patterns-- `neural/compress` - Simulate compression-- `neural/status` - Get neural system status-- `neural/optimize` - Simulate optimization--**performance-tools.ts** (6 tools) - β οΈ Mostly illustrative:-- `performance/report` - Generate performance report-- `performance/bottleneck` - Detect bottlenecks (simulated)-- `performance/benchmark` - Run benchmarks (simulated results)-- `performance/profile` - Profile component (simulated)-- `performance/optimize` - Apply optimizations (state only)-- `performance/metrics` - Get metrics (illustrative)-**github-tools.ts** (5 tools) - β οΈ Local state only, no GitHub API:- `github/repo_analyze` - Store local repo analysis record- `github/pr_manage` - Manage local PR records