🌊 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
docs: add badges, links, and SEO-optimized keywords
Claude02df9fd2f3fb
diff --git a/v3/@claude-flow/guidance/README.md b/v3/@claude-flow/guidance/README.mdindex b7e02b1071..b7a479049d 100644--- a/v3/@claude-flow/guidance/README.md+++ b/v3/@claude-flow/guidance/README.md@@ -1,5 +1,15 @@# @claude-flow/guidance+[](https://www.npmjs.com/package/@claude-flow/guidance)+[](https://www.npmjs.com/package/@claude-flow/guidance)+[](https://github.com/ruvnet/claude-flow/blob/main/LICENSE)+[](https://github.com/ruvnet/claude-flow)+[](https://nodejs.org)+[](https://www.typescriptlang.org/)+[](https://github.com/ruvnet/claude-flow)+[](https://www.npmjs.com/package/claude-flow)+[](https://www.npmjs.com/package/ruvbot)+**Long-horizon governance for Claude Code agents.**AI coding agents are powerful for short tasks, but they break down over long sessions. They forget rules, repeat mistakes, run in circles, corrupt their own memory, and eventually need a human to step in. The longer the session, the worse it gets.@@ -1167,6 +1177,19 @@ If B beats A by 0.2 on that score across three task classes, you have a categoryTake 20 real Claude Flow tasks from repo history. Run A without control plane, run B with Phase 1 only. Success is B improves success rate and reduces tool calls per successful task, while producing replayable ledgers for every failure.+## Links++| Resource | URL |+|----------|-----|+| **GitHub** | [github.com/ruvnet/claude-flow](https://github.com/ruvnet/claude-flow) |+| **npm: @claude-flow/guidance** | [npmjs.com/package/@claude-flow/guidance](https://www.npmjs.com/package/@claude-flow/guidance) |+| **npm: claude-flow** | [npmjs.com/package/claude-flow](https://www.npmjs.com/package/claude-flow) |+| **npm: ruvbot** | [npmjs.com/package/ruvbot](https://www.npmjs.com/package/ruvbot) |+| **ruv.io** | [ruv.io](https://ruv.io) |+| **Issues** | [github.com/ruvnet/claude-flow/issues](https://github.com/ruvnet/claude-flow/issues) |+| **API Reference** | [docs/reference/api-quick-reference.md](docs/reference/api-quick-reference.md) |+| **ADR Index** | [docs/adrs/](docs/adrs/) |+## License-MIT+MIT — see [LICENSE](https://github.com/ruvnet/claude-flow/blob/main/LICENSE) for details.diff --git a/v3/@claude-flow/guidance/package.json b/v3/@claude-flow/guidance/package.jsonindex af2d07feb6..0545868dcb 100644--- a/v3/@claude-flow/guidance/package.json+++ b/v3/@claude-flow/guidance/package.json@@ -154,12 +154,35 @@},"keywords": ["claude-flow",+ "claude-code",+ "claude",+ "anthropic",+ "ai-agent",+ "ai-governance",+ "agent-governance","guidance","control-plane",- "policy",- "enforcement",- "hooks",- "optimization"+ "policy-enforcement",+ "enforcement-gates",+ "proof-chain",+ "trust-system",+ "long-horizon",+ "autonomous-agent",+ "claude-md",+ "CLAUDE.md",+ "memory-governance",+ "adversarial-defense",+ "prompt-injection",+ "wasm",+ "ruvbot",+ "ruv",+ "ai-safety",+ "agent-orchestration",+ "multi-agent",+ "code-generation",+ "llm-governance",+ "mcp",+ "model-context-protocol"],"author": "Claude Flow Team","license": "MIT",