libagent
libagent - Agent orchestration library for conversational AI. AgentMind class coordinates LLM completions, memory management, tool execution, and multi-turn conversations. AgentAction handles tool calls and action processing. Use for building chat agents, RAG pipelines, and AI assistants. Integrates with libmemory, librpc, and libllm
npx skills add majiayu000/claude-skill-registry --skill libagent --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# libagent Skill ## When to Use - Building conversational AI agents with tool capabilities - Coordinating LLM completions with memory context - Processing multi-turn conversations with state - Implementing RAG (retrieval-augmented generation) pipelines ## Key Concepts **AgentMind**: Core reasoning engine that processes requests through LLM completions, manages conversation state, and coordinates tool execution. **AgentAction**: Handles individual tool calls, executes actions, and returns results to the conversation flow. ## Usage Patterns ### Pattern 1: Basic agent request ```javascript import { AgentMind } from "@copilot-ld/libagent"; const mind = new AgentMind(memoryClient, llmClient, toolClient); const response = await mind.process({ resourceId: conversationId, content: "What is the weather?", }); ``` ### Pattern 2: Streaming responses ```javascript for await (const chunk of mind.stream(request)) { process.stdout.write(chunk.content); } ``` ## Integration Works with `libmemory` for context windows, `librpc` for gRPC clients, and `libllm` for completions. Used by the Agent service.
- When to Use
- Key Concepts
- Usage Patterns
- Pattern 1: Basic agent request
- Pattern 2: Streaming responses
- Integration
What does the libagent skill do?
libagent - Agent orchestration library for conversational AI. AgentMind class coordinates LLM completions, memory management, tool execution, and multi-turn conversations. AgentAction handles tool calls and action processing. Use for building chat agents, RAG pipelines, and AI assistants. Integrates with libmemory, librpc, and libllm
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill libagent --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.