omnicoreagent 0.3.9

OmniCoreAgent is an open Python agent harness for building autonomous AI agents that use tools, manage memory and context, coordinate workflows, and handle production business logic.

OmniCoreAgent

The Open Agent Harness Built for Production
Parallel tool batches. Structured observations. Loop detection. Memory, workspace files, MCP, subagents, and serving in one runtime.

Quick Start - What Makes It Different - Cookbook - Features - Docs

---

Quick Start

pip install omnicoreagent

echo "LLM_API_KEY=your_api_key" > .env

import asyncio
from omnicoreagent import OmniCoreAgent

agent = OmniCoreAgent(
    name="assistant",
    system_instruction="You are a helpful assistant.",
    model_config={"provider": "openai", "model": "gpt-4o"},
)

async def main():
    result = await agent.run("Research the top 3 AI frameworks and summarize them.")
    print(result["response"])
    await agent.cleanup()

asyncio.run(main())

That is the smallest path: one agent, one model, the harness loop, session memory, guardrails, workspace files, error handling, and metrics around each run.

Context management, tool output offloading, BM25 tool retrieval, subagents, skills, cloud workspace storage, and production backends are opt-in so a small agent stays small.

Ready to go deeper? The Cookbook has progressive examples from hello world to production deployments.

---

What Makes It Different

Most agent frameworks stop at "LLM plus tool loop." OmniCoreAgent is built around the problems that show up after that: slow sequential tools, noisy observations, stuck loops, context exhaustion, MCP server tools, durable workspace files, and runtime serving.

1. Agents call tools in batches instead of forced sequences

The usual tool loop looks like this:

LLM -> call tool A -> wait -> result -> LLM -> call tool B -> wait -> result

OmniCoreAgent lets the model request independent tools together:

LLM -> [tool A + tool B + tool C in parallel] -> one structured observation -> LLM

The model gets one complete view of the batch before it reasons again. A failed tool is represented beside the successful tools instead of silently collapsing the whole step.

Native function calling alone is not the runtime. OmniCoreAgent uses its own tool-call contract, parser, resolver, parallel runner, and result formatter so the harness controls the full execution path.

2. Tool results become structured observations

Raw tool output is often too noisy for the next reasoning step. Large payloads, errors, irrelevant fields, and prompt-injection content can all distort the loop.

OmniCoreAgent routes tool results through an observation pipeline:

tool output -> parse -> format -> guardrail check -> offload when configured -> observation -> model

The model receives the signal it needs to continue the task, not an unbounded dump of every byte returned by a tool. When tool offloading is enabled, large outputs are written into the active workspace and the model receives a readable preview plus a path it can use later.

3. Loop detection uses signatures beyond step counts

max_steps is still useful, but it is a blunt instrument. It stops an agent that is making progress just as quickly as one that is stuck.

OmniCoreAgent tracks SHA256-backed tool-call signatures across the loop. Each signature is based on the tool name, input, and output for the call. The runtime detects:

• Consecutive loops: the same tool call returns the same result repeatedly.
• Pattern loops: the same tool repeats a small interaction pattern.

When the harness stops a loop, the agent gets a reason. That makes debugging the agent behavior much easier than "max iterations reached."

4. The harness is already assembled

OmniCoreAgent ships as a working agent harness, not a bag of disconnected pieces:

model + prompt + loop + tools + memory + context + workspace + guardrails + events

Keep it small for simple agents, then turn on the heavier harness pieces when the workload needs them: MCP tools, BM25 tool retrieval, dynamic subagents, skills, cloud workspace storage, Redis/Postgres/MongoDB memory, event streams, and OmniServe.

5. Context is managed before the model call

When context management is enabled, OmniCoreAgent checks the active message history before every LLM request. If the configured threshold is crossed, the harness automatically applies the selected strategy before calling the model:

messages -> threshold check -> truncate or summarize+truncate -> LLM

The system prompt is preserved, recent messages are preserved, and older middle history is either summarized or removed depending on configuration. If you set the budget below your model's real context window, the harness acts before the provider rejects the request.

---

Implementation Map

OmniCoreAgent's capabilities are backed by concrete runtime modules:

Capability	Where It Lives
Parallel tool batches	core/tools/tool_batch_runner.py
XML tool-call contract	core/agents/xml_parser.py
Structured observations	core/tools/tool_observation.py
Tool output offloading	core/workspace/artifacts.py
Automatic context control	core/agents/llm_step.py, core/context_manager.py
Workspace files	core/workspace/tools.py, core/workspace/storage.py
Dynamic subagents	core/subagents.py
Loop detection	core/agents/loop_detection.py
MCP server tools	mcp_clients_connection/client.py
OmniServe	serve/

See the Agent Harness docs for the full implementation map.

---

See It In Action

import asyncio
from omnicoreagent import MemoryRouter, OmniCoreAgent, ToolRegistry

tools = ToolRegistry()

@tools.register_tool("search_web")
def search_web(query: str) -> dict:
    """Search the web for information."""
    return {"results": [f"Result for: {query}"]}

@tools.register_tool("read_file")
def read_file(path: str) -> dict:
    """Read a local project file."""
    return {"path": path, "content": f"Contents of {path}"}

agent = OmniCoreAgent(
    name="research-agent",
    system_instruction=(
        "You are a research assistant. Use tools in parallel when the calls are "
        "independent and you can reason over the results together."
    ),
    model_config={"provider": "openai", "model": "gpt-4o"},
    local_tools=tools,
    memory_router=MemoryRouter("in_memory"),
    agent_config={
        "max_steps": 20,
        "context_management": {"enabled": True},
        "tool_offload": {"enabled": True},
        "enable_subagents": True,
        "enable_advanced_tool_use": True,
    },
)

async def main():
    result = await agent.run(
        "Search for recent AI agent papers and read notes.md. Do both at once "
        "if neither depends on the other."
    )
    print(result["response"])
    await agent.cleanup()

asyncio.run(main())

The runtime accepts search_web and read_file in the same batch, returns both results together, and continues from one structured observation.

---

Install Only What You Need

pip install omnicoreagent                    # Core runtime
pip install "omnicoreagent[redis]"           # Redis memory + event streams
pip install "omnicoreagent[postgres]"        # PostgreSQL / SQL memory
pip install "omnicoreagent[mongodb]"         # MongoDB memory
pip install "omnicoreagent[s3]"              # S3 / R2 workspace storage
pip install "omnicoreagent[serve]"           # OmniServe REST/SSE API
pip install "omnicoreagent[all]"             # Everything

Production backends are installable extras. Install only what the agent actually uses.

---

Features

Feature	What It Does
Parallel Batch Tool Execution	Executes independent tool calls concurrently and returns one combined observation to the model.
Structured Observation Pipeline	Parses, formats, guardrail-checks, and offloads tool results when configured before the model sees them.
Signature-Based Loop Detection	Detects repeated SHA256-backed tool-call signatures and repeated tool interaction patterns beyond step-count exhaustion.
MCP Native Tools	Connects MCP servers over stdio, SSE, and Streamable HTTP, including OAuth-capable remote servers.
Local Tool Registry	Registers Python functions as tools with inferred schemas and async/sync execution support.
Multi-Tier Memory	Uses in-memory, SQLite, Redis, MongoDB, or SQL-backed session history through the memory router.
Runtime Backend Switching	Switches memory and event backends at runtime when configured.
Workspace Files	Gives agents a local, S3, or R2-backed file workspace for notes, scratchpads, artifacts, and tool offloads.
Context Engineering	Checks context before each model call and automatically truncates or summarizes when the configured budget threshold is crossed.
Tool Output Offloading	Writes large tool results to workspace files and gives the model a preview plus a file reference.
Dynamic Subagents	Lets the main agent spawn focused workers with isolated context and shared workspace output.
Agent Skills	Loads packaged capabilities implemented with Python, Bash, or Node.js.
BM25 Tool Retrieval	Selects relevant tools from large tool sets so the prompt stays focused.
Guardrails	Adds prompt-injection screening inside the observation path with configurable behavior.
Event System	Emits structured runtime events for agent runs, tool calls, and streaming integrations.
Workflow Orchestration	Provides sequential, parallel, and router agents for multi-step application workflows.
Background Agents	Supports scheduled autonomous tasks for interval-based workloads.
Universal Models	Routes through LiteLLM to OpenAI, Anthropic, Gemini, Groq, Ollama, DeepSeek, Mistral, OpenRouter, Azure, and Cencori.
OmniServe	Turns an agent into a REST/SSE service with lifecycle management and metrics.

---

Cookbook

All examples live in the Cookbook and are organized by use case.

Category	What You'll Build
Getting Started	First agent, tools, memory, events
Workflows	Sequential, Parallel, Router agents
Background Agents	Scheduled autonomous tasks
Production	Guardrails, serving, and production patterns

---

Configuration

Environment Variables

# Required by most hosted model providers
LLM_API_KEY=your_api_key

# Workspace storage
OMNICOREAGENT_WORKSPACE_BACKEND=local   # local | s3 | r2
OMNICOREAGENT_WORKSPACE_DIR=.omnicoreagent/workspace
AWS_S3_BUCKET=your-s3-bucket            # when backend=s3
R2_BUCKET_NAME=your-r2-bucket           # when backend=r2

Agent Config Reference

agent_config = {
    "max_steps": 15,
    "tool_call_timeout": 30,
    "request_limit": 0,                  # 0 = unlimited
    "total_tokens_limit": 0,             # 0 = unlimited
    "memory_config": {
        "mode": "sliding_window",
        "value": 10000,
        "summary": {"enabled": False},
    },
    "enable_workspace_files": True,      # Default on
    "guardrail_mode": "full",            # Default guardrail mode
    "context_management": {"enabled": True},
    "tool_offload": {"enabled": True},
    "enable_advanced_tool_use": True,
    "enable_subagents": True,
    "enable_agent_skills": True,
}

When enable_subagents is true, workspace files are enabled automatically so subagents write outputs, notes, todos, and artifacts into the active workspace.

Full reference: Configuration Guide

---

Development

git clone https://github.com/omnirexflora-labs/omnicoreagent.git
cd omnicoreagent

uv venv && source .venv/bin/activate
uv sync --dev

pytest tests/ -v
pytest tests/ --cov=src --cov-report=term-missing

---

Troubleshooting

Error	Fix
Invalid API key	Set the right provider key in .env, for example LLM_API_KEY, OPENAI_API_KEY, or ANTHROPIC_API_KEY.
ModuleNotFoundError for Redis / Postgres / MongoDB / S3	Install the matching extra, for example pip install "omnicoreagent[redis]".
Redis connection failed	Start Redis or use MemoryRouter("in_memory").
MCP connection refused	Ensure the MCP server is running before starting the agent.

More help: Basic Usage Guide

---

Contributing

git clone https://github.com/omnirexflora-labs/omnicoreagent.git
cd omnicoreagent

uv venv && source .venv/bin/activate
uv sync --dev
pre-commit install

See CONTRIBUTING.md for guidelines. PRs are welcome.

---

License

MIT - see LICENSE.

---

Author

Built by Abiola Adeshina.

• GitHub: @Abiorh001
• X (Twitter): @abiorhmangana
• Email: [e-mail]

The OmniRexFlora Ecosystem

Project	Description
OmniMemory	Self-evolving memory for autonomous agents
OmniCoreAgent	Production agent harness (this project)
OmniDaemon	Event-driven runtime for running agents as supervised, autonomous infrastructure services

Built On

LiteLLM - FastAPI - Redis - Pydantic - APScheduler

---

Star on GitHub - Report Bug - Request Feature - Documentation