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
rUvf86dabb63ab8
diff --git a/README.md b/README.mdindex 49693dc91b..c129e26360 100644--- a/README.md+++ b/README.md@@ -53,7 +53,9 @@ npx claude-flow@v3alpha init----### π **Core Flow** β How requests move through the system+<details>+<summary><strong>Core Flow</strong> β How requests move through the system</summary>+| Layer | Components | What It Does ||-------|------------|--------------|| User | Claude Code, CLI | Your interface to control and run commands |@@ -61,13 +63,21 @@ npx claude-flow@v3alpha init| Agents | 54+ types | Specialized workers (coder, tester, reviewer...) || Providers | Anthropic, OpenAI, Google, Ollama | AI models that power reasoning |-### π **Swarm Coordination** β How agents work together+</details>++<details>+<summary><strong>Swarm Coordination</strong> β How agents work together</summary>+| Layer | Components | What It Does ||-------|------------|--------------|| Coordination | Queen, Swarm, Consensus | Manages agent teams (Raft, Byzantine, Gossip) || Drift Control | Hierarchical topology, Checkpoints | Prevents agents from going off-task |-### π§ **Intelligence & Memory** β How the system learns and remembers+</details>++<details>+<summary><strong>Intelligence & Memory</strong> β How the system learns and remembers</summary>+| Layer | Components | What It Does ||-------|------------|--------------|| Memory | HNSW, AgentDB, Cache | Stores and retrieves patterns 150x faster |@@ -75,13 +85,21 @@ npx claude-flow@v3alpha init| Learning | SONA, MoE, ReasoningBank | Self-improves from results (<0.05ms adaptation) || Fine-tuning | MicroLoRA, EWC++ | Lightweight adaptation without full retraining |-### β‘ **Optimization** β How to reduce cost and latency+</details>++<details>+<summary><strong>Optimization</strong> β How to reduce cost and latency</summary>+| Layer | Components | What It Does ||-------|------------|--------------|| Agent Booster | WASM, AST analysis | Skips LLM for simple edits (<1ms) || Token Optimizer | Compression, Caching | Reduces token usage 30-50% |-### π§ **Operations** β Background services and integrations+</details>++<details>+<summary><strong>Operations</strong> β Background services and integrations</summary>+| Layer | Components | What It Does ||-------|------------|--------------|| Background | Daemon, 12 Workers | Auto-runs audits, optimization, learning |@@ -90,7 +108,10 @@ npx claude-flow@v3alpha init| GitHub | PR, Issues, Workflows | Manages repos and code reviews || Analytics | Metrics, Benchmarks | Monitors performance, finds bottlenecks |-### π― Task Routing β Extend your Claude Code subscription by 250%+</details>++<details>+<summary><strong>Task Routing</strong> β Extend your Claude Code subscription by 250%</summary>Smart routing skips expensive LLM calls when possible. Simple edits use WASM (free), medium tasks use cheaper models. This can extend your Claude Code usage by 250% or save significantly on direct API costs.@@ -100,6 +121,8 @@ Smart routing skips expensive LLM calls when possible. Simple edits use WASM (fr| Medium | Haiku/Sonnet | ~500ms || Complex | Opus + Swarm | 2-5s |+</details>+### Claude Code: With vs Without Claude-Flow| Capability | Claude Code Alone | Claude Code + Claude-Flow |diff --git a/agents/architect.yaml b/agents/architect.yamlindex 61db099700..0d0ca0a00f 100644--- a/agents/architect.yaml+++ b/agents/architect.yaml@@ -8,4 +8,4 @@ capabilities:optimizations:- context-caching- memory-persistence-createdAt: "2026-01-15T16:39:17.735Z"+createdAt: "2026-01-15T20:50:37.815Z"diff --git a/agents/coder.yaml b/agents/coder.yamlindex fc042031f2..ba57477c8a 100644--- a/agents/coder.yaml+++ b/agents/coder.yaml@@ -8,4 +8,4 @@ capabilities:optimizations:- flash-attention- token-reduction-createdAt: "2026-01-15T16:39:17.734Z"+createdAt: "2026-01-15T20:50:37.815Z"diff --git a/agents/reviewer.yaml b/agents/reviewer.yamlindex 38dad92a33..577782d384 100644--- a/agents/reviewer.yaml+++ b/agents/reviewer.yaml@@ -7,4 +7,4 @@ capabilities:- best-practicesoptimizations:- incremental-analysis-createdAt: "2026-01-15T16:39:17.735Z"+createdAt: "2026-01-15T20:50:37.815Z"diff --git a/agents/security-architect.yaml b/agents/security-architect.yamlindex 6a004f20fb..4c593a0514 100644--- a/agents/security-architect.yaml+++ b/agents/security-architect.yaml@@ -7,4 +7,4 @@ capabilities:- security-reviewoptimizations:- pattern-matching-createdAt: "2026-01-15T16:39:17.735Z"+createdAt: "2026-01-15T20:50:37.815Z"diff --git a/agents/tester.yaml b/agents/tester.yamlindex 91907a0356..884f7521a9 100644--- a/agents/tester.yaml+++ b/agents/tester.yaml@@ -7,4 +7,4 @@ capabilities:- coverageoptimizations:- parallel-execution-createdAt: "2026-01-15T16:39:17.735Z"+createdAt: "2026-01-15T20:50:37.815Z"