forge

A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows

21 articles 1.6k View on GitHub ↗
21 articles
How to Configure Backend-Specific Native Function Calling in Forge

Learn to configure backend-specific native function calling in Forge. Set mode native, use the --jinja flag for Llamafile, and pass ToolSpec objects for seamless integration.

how-to-guide
May 22, 2026
How to Manage Multi-Turn Conversation History with WorkflowRunner

Easily manage multi-turn conversation history with WorkflowRunner. Pass message history via initial_messages and capture new messages with on_message for stateful AI bots.

how-to-guide
May 22, 2026
How SlotWorker Handles Priority Queuing and Auto‑Preemption in Forge

Discover how SlotWorker uses asyncio PriorityQueue and auto-preemption to manage urgent tasks, ensuring efficient workflow execution in Forge.

internals
May 22, 2026
How to Implement Custom CompactStrategy Subclasses in Forge

Learn how to implement custom CompactStrategy subclasses in Forge by extending the abstract base class and implementing the compact() method. Preserve system prompts easily.

how-to-guide
May 22, 2026
How to Troubleshoot Validation Failures in Forge Proxy Mode

Troubleshoot validation failures in Forge proxy mode by identifying errors in response validation, retry budget, or tool specs. Learn how to fix LLM rejections.

how-to-guide
May 22, 2026
How Forge Measures Tool-Calling Reliability: Message History Analysis in the Evaluation Harness

Forge measures tool-calling reliability by analyzing message history. Discover how retry nudges, step violations, tool errors, and wasted calls are quantified within the evaluation harness.

deep-dive
May 22, 2026
How to Configure Recommended Sampling Parameters per Model in Forge

Easily configure recommended sampling parameters per model in Forge. Learn how to apply official Hugging Face sampling defaults with recommended_sampling=True for optimal results.

how-to-guide
May 22, 2026
Context Budget Resolution in Forge: How Token Allocation Works Across Ollama, Llama-Server, and Llamafile Backends

Understand context budget resolution in Forge. Discover how token allocation works across Ollama, Llama-Server, and Llamafile backends using backend discovery and BudgetMode strategies.

how-to-guide
May 22, 2026
How to Implement Tool Prerequisites in Forge Workflows: A Complete Guide

Learn how to implement tool prerequisites in Forge workflows. Ensure tools run only after predecessors complete with this complete guide for the antoinezambelli/forge repository.

how-to-guide
May 22, 2026
How Forge Retry Logic Handles Validation Failures with Nudges

Discover how Forge retry logic handles validation failures with nudges. Learn how Forge prompts model correction and enforces retry limits for robust error management.

how-to-guide
May 22, 2026
How to Integrate Forge with an Ollama Backend: Complete Configuration Guide

Integrate Forge with Ollama using the OllamaClient for seamless synchronous and streaming inference. Configure your project effortlessly with this comprehensive guide.

how-to-guide
May 22, 2026
How the Synthetic Respond Tool Improves Small Model Accuracy in Forge

Learn how the synthetic respond tool boosts small model accuracy in Forge by forcing tool-calling mode, eliminating ambiguity, and ensuring response validation.

deep-dive
May 22, 2026

Have a question about this repo?

These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:

Share the following with your agent to get started:
curl -s "https://instagit.com/install.md"
Works with
Claude Codex Cursor VS Code OpenClaw Any MCP Client

Maintain an open-source project? Get it listed too →