Documentation Index
Fetch the complete documentation index at: https://docs-omnicoreagent.omnirexfloralabs.com/llms.txt
Use this file to discover all available pages before exploring further.

Open Python Agent Harness For Production AI Applications
OmniCoreAgent is the harness around the model: the loop, tools, memory, context control, workspace files, MCP tools, subagents, background tasks, and REST/SSE serving boundary that make an agent usable beyond a demo. Start small with one agent and one model. Add tools, memory, workspace files, background tasks, telemetry, and OmniServe only when the application needs them.Run The Quickstart
Install OmniCoreAgent, create your first agent, add one tool, and learn the
next paths.
Use Docs With AI Tools
Use Ask AI, Markdown export,
llms.txt, hosted docs MCP, Cursor, VS Code,
ChatGPT, Claude, and Perplexity.Choose Your Path
Build Your First Agent
One model, one agent, one task.
Add Python Tools
Register application-owned functions with
ToolRegistry.Connect MCP Tools
Load tools from external MCP servers.
Keep Session Memory
Store conversation history in memory, Redis, MongoDB, or SQL.
Use Workspace Files
Give agents a file surface for notes, artifacts, and offloads.
Serve An Agent API
Run the same agent behind REST and SSE endpoints.
Run Background Work
Schedule durable agent work with run history, retries, and workspace output.
Build A Real Application
Start from production-shaped examples.
Why It Exists
OmniCoreAgent is built around real agent runtime problems:Parallel tool batches
The runtime supports independent tool calls in one batch, executes them
concurrently, and returns one structured observation.
Structured observations
Tool results are parsed, formatted, guardrail-checked, and offloaded when
they cross the configured threshold before the model sees them.
Signature loop detection
The harness detects repeated tool signatures and repeated tool interaction
patterns beyond max-step exhaustion.
Workspace-backed context
Agents, subagents, tool offloads, notes, scratchpads, and artifacts share one
local, S3, or R2-backed workspace.
Automatic context control
When enabled, the runtime checks context before each model call and acts
before the configured budget is exceeded.
Start Building
Quick Start
Build your first OmniCoreAgent and run a task.
Agent Harness
Understand what OmniCoreAgent adds around the model.
Installation
Install the core package or the extras your agent uses.
Local Tools
Register application-owned Python functions as tools.
MCP Tools
Connect external MCP servers over stdio, SSE, or Streamable HTTP.
Configuration
Environment variables, memory, workspace, task stores, telemetry, and
OmniServe settings.
OmniServe
Production REST/SSE serving, auth, rate limits, events, and background APIs.
See It In Action
Core Documentation
OmniCoreAgent
The main agent harness API and runtime capabilities.
Agent Harness
The implementation-backed map of the runtime pieces around the model.
Architecture
How the loop, tools, observations, memory, workspace, and serving layers fit.
Memory
Session history across in-memory, Redis, MongoDB, and SQL database storage.
Context Engineering
Context strategies plus tool-output offloading for long-running tasks.
Workspace Files
Local, S3, or R2 files for notes, scratchpads, artifacts, and offloads.
Subagents
Dynamic focused workers that write outputs back into the workspace.
Guardrails
Prompt-injection screening inside the observation pipeline.
Events
Runtime events for runs, tool calls, and streaming integrations.
OmniServe
Run an OmniCoreAgent behind REST and SSE endpoints.