Skip to main content

Getting Started with OmniCoreAgent

Welcome to the OmniCoreAgent learning path. This guide takes you from writing your first line of code to building production-ready, autonomous agents with persistent memory, context management, and guardrails. Follow the examples in order โ€” each one builds on the concepts from the previous.

๐Ÿ“š The Learning Path


๐ŸŽฏ โ€œI just want toโ€ฆโ€


๐Ÿ› ๏ธ Prerequisites

The examples start with in-memory defaults. Add REDIS_URL, DATABASE_URL, or MONGODB_URI only when you intentionally run the persistence examples.

๐Ÿ“– Key Concepts

Memory with Summarization

Old messages are summarized, not lost.

Context Management

Long conversations stay within the context budget you configure.

Choosing the Right Mode

Trade-offs: Recommendations:
  • Chatbots / Q&A agents: Use sliding_window with value: 10-20
  • Tool-heavy agents (APIs, web scraping): Use token_budget with value: 8000-16000
  • Mixed workloads: Use token_budget with lower threshold (50-60%)

Tool Response Offloading

Large tool responses are automatically saved into the active workspace artifacts/ area, with only a preview in context. How it works:
  1. Tool returns large response (e.g., web search with 50 results)
  2. Response saved to workspace/artifacts/
  3. Agent sees preview + file reference in context
  4. Agent uses read_artifact() tool to get full content when needed
Token savings example: Tool offloading adds 4 artifact tools:
  • read_artifact(artifact_id) - Read full content
  • tail_artifact(artifact_id, lines) - Read last N lines
  • search_artifact(artifact_id, query) - Search within artifact
  • list_artifacts() - List all offloaded artifacts
Workspace files are separate and enabled by default with workspace-scoped command tools such as ls, read_file, write_file, glob, and grep.
๐Ÿ’ก Inspired by Cursorโ€™s โ€œdynamic context discoveryโ€ and Anthropicโ€™s context engineering patterns

Guardrails

Built-in protection against prompt injection attacks.

Metrics

Track usage for cost control and monitoring.

๐Ÿš€ Next Steps

Live text

Run python cookbook/getting_started/agent_with_streaming.py to consume live text and a terminal outcome. Intermediate text is not the final answer; check the terminal status. Closing the iterator cancels the run.