agentica-sdk
Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration
Discover tools llm ai skills, compare source repositories and read the instructions for each workflow.
Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration
Research agent for external documentation, best practices, and library APIs via MCP tools
Guide to the math cognitive stack - what tools exist and when to use each
Create and configure Claude Code sub-agents with custom prompts, tools, and models
Background Agent Pings
LLM Tuning Patterns
Spawn Agentica multi-agent patterns
Reference guide for Agentica multi-agent infrastructure APIs
Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
Agent Context Isolation
Semantic search across codebase using LEANN vector index
AI-powered web search, research, and reasoning via Perplexity
Goal-based workflow orchestration - routes tasks to specialist agents based on user goals
Agent Orchestration Rules
Meta-skill for creating and managing Claude Code skills
Guide for integrating Agentica SDK with Claude Code CLI proxy
Deterministic router for math cognitive stack - maps user intent to exact CLI commands
Unified math capabilities - computation, solving, and explanation. I route to the right tool.
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
Parallel Agent Orchestration
Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".
Create and use Claude Code slash commands - quick prompts, bash execution, file references
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.