Orchestration Engine

Intelligent Task Orchestration

Agent doesn't follow fixed scripts. It decomposes tasks on its own, runs multiple steps concurrently, and auto-adjusts plans when problems arise — like a thinking executor, not a button-pressing robot.

Standard Mode

available

Agent thinks and acts step by step. After each step, it decides what to do next based on results. Ideal for tasks requiring judgment and trial-and-error, like alert investigation, document analysis, and information retrieval.

Supports native Function Calling (OpenAI-style) and JSON-mode reasoning
Auto-recovers from errors
Send supplementary messages during execution, injected at the next step
Auto re-planning: adjusts approach when goals aren't met, up to 3 rounds
Each step runs a full think-act loop internally
Interactive flowchart showing real-time node status, dependencies, and execution time
Multi-turn conversation support with automatic history context management

Planning Mode

available

Agent first creates a complete execution plan, decomposing tasks into steps and identifying dependencies — independent steps run concurrently, dependent steps run sequentially. After completion, it checks results and auto-retries with adjusted plans if goals aren't met.

Standard ModePlanning Mode
How it worksStep-by-step thinking and actingPlan first, then parallel execution
Best forTasks requiring judgment and trial-and-errorMulti-step, parallelizable tasks
Self-correctionAuto-recovers from errorsAuto re-plans when goals aren't met
VisualizationStep-by-step reasoning displayInteractive flowchart with real-time status

Visual Pipeline (Blueprint Mode)

coming

For teams who prefer drag-and-drop, a visual pipeline editor with three progressive levels:

1Fully Static: Like Dify workflows — each node performs a fixed operation with deterministic I/O connections
2Semi-Dynamic: Key nodes upgrade to Agent mode, reasoning autonomously within predefined tools and knowledge bases
3Fully Dynamic: No static pipeline, Agent plans and executes completely autonomously

Built-in scenario templates (contract review, financial reconciliation, approval assistance, etc.), forkable and customizable.

Context Management

available

Long conversations auto-compress earlier content while preserving recent text verbatim. Critical information (task descriptions, user corrections) is protected from compression. A unified token budget manager ensures conversations always stay within the model's context window.

Developers

Get started in 3 minutes

git clone https://github.com/fim-ai/fim-agent.git && ./start.sh

Enterprise

Learn how FIM Agent fits your enterprise. Get a customized deployment plan.