AI Agent Frameworks · Public

forge

Agent SDK framework for checking tool contracts, handoffs, guardrails, traces, and multi-agent coordination boundaries.

Best fitDevelopers building traceable, reviewable, acceptance-tested agent workflows.

Check whether this project matches your task before installing it.

What it can doAgent workflow modeling, tool contracts, handoff design, guardrail review, traces, and acceptance checks

Review the portable capability path.

Before continuingVerify in a sandbox

Do not treat a preview pack as a proven local install.

GitHub snapshotstars unavailable

forks unavailable · contributors unavailable

Official first step Read manual preview Source repository

Publication status · 2026-05-20

What is forge?

forge helps build agent workflows with tools, handoffs, guardrails, traces, and acceptance boundaries.
Best fit: Developers building traceable, reviewable, acceptance-tested agent workflows.
Not for: Not for one-off prompts or flows without tool permission boundaries and traces.
Capability added to an AI workflow: Agent workflow modeling, tool contracts, handoff design, guardrail review, traces, and acceptance checks
First safe verification step: Build one minimal agent with a harmless tool, then verify trace, handoff or guardrail, and failure behavior.
Verification state: source, Quick Start, and sandbox install checks are recorded as passed.
Top risk: The main risk is treating an agent example as production design without tool permissions, guardrails, traces, and approvals.
Evidence base: https://github.com/antoinezambelli/forge, https://news.ycombinator.com/item?id=48192383, https://github.com/antoinezambelli/forge#readme, Human Manual

Quick decision

Use this section to decide whether the project is worth a deeper read.

Best forDevelopers building traceable, reviewable, acceptance-tested agent workflows.

Match the project to your task before installing it.

CapabilityAgent workflow modeling, tool contracts, handoff design, guardrail review, traces, and acceptance checks

Agent SDK framework for checking tool contracts, handoffs, guardrails, traces, and multi-agent coordination boundaries.

Repositoryantoinezambelli/forge

stars unavailable · forks unavailable

What it can do

Translate the upstream project into concrete capabilities the user can judge before installing.

Introduction to Forge

Related topics: System Architecture, Quick Start Guide

Sources: [README.md](https://github.com/antoinezambelli/forge/blob/main/README.md)

Installation Guide

Related topics: Backend Setup Guide, Quick Start Guide

Source: https://github.com/antoinezambelli/forge / Human Manual

Quick Start Guide

Related topics: WorkflowRunner and Agentic Loop, System Architecture

Sources: [README.md:1-20](https://github.com/antoinezambelli/forge/blob/main/README.md)

System Architecture

Related topics: WorkflowRunner and Agentic Loop

Sources: [CONTRIBUTING.md](https://github.com/antoinezambelli/forge/blob/main/CONTRIBUTING.md)

Module Structure and API

Related topics: System Architecture, WorkflowRunner and Agentic Loop

Sources: [src/forge/__init__.py]()

Sources: https://github.com/antoinezambelli/forge, Human Manual, Project Pack evidence, and downstream validation signals.

Community Discussion Evidence

Project-level external discussion stays visible on the detail page, not only inside the manual.

Starsstars unavailable

Forksforks unavailable

Contributorscontributors unavailable

Licenseunknown

Community Discussion Evidence

10 source-linked items

Review these external discussions before using forge with real data or production workflows. They are review inputs, not standalone proof that the project is production-ready.

01
Hardware detection: AMD unified-memory rigs fall through to 4K Ollama bu
github / github_issue
02
Per-model recommended sampling defaults (map keyed by HF model cards)
github / github_issue
03
Client sampling params: thread top_p/top_k/min_p/repeat_penalty through
github / github_issue
04
llama.cpp reasoning budget sampler causes silent hangs after April 10 bu
github / github_issue
05
Rescue-parse ChatGPT-style XML tool calls
github / github_issue
06
Proxy external mode hardcodes native FC — no prompt-injection fallback
github / github_issue
07
Investigate: integration paths with Hermes Agent
github / github_issue
08
Sub-agent support: slot pool
github / github_issue
09
Sub-agent support: dynamic slot splitting
github / github_issue
10
README/documentation is current enough for a first validation pass.
GitHub / issue

How to start

Only source-backed commands are shown here. Verify them in an isolated environment first.

Try the prompt first

Test the workflow without installing the upstream project.

preview

Read the Human Manual

Understand inputs, outputs, limits, and failure modes.

manual

Take context to your AI host

Use the compiled assets in your preferred AI environment.

context

Run sandbox verification

Confirm install commands and rollback before using a primary environment.

verify

pip install forge-guardrails

Official start command · https://github.com/antoinezambelli/forge#readme · verified: yes

Human Manual

The English page must expose the real manual, not a short placeholder.

8+ sections · Human Manual

forge Manual

Forge addresses the core challenges of LLM-based agent development:

Open the full manual

forge Human Manual
Table of Contents
Introduction to Forge
Related Pages
Overview
Core Architecture
Project Structure
Quick Start

Introduction to Forge

Related topics: System Architecture, Quick Start Guide

Sources: [README.md](https://github.com/antoinezambelli/forge/blob/main/README.md)

Installation Guide

Related topics: Backend Setup Guide, Quick Start Guide

Source: https://github.com/antoinezambelli/forge / Human Manual

Quick Start Guide

Related topics: WorkflowRunner and Agentic Loop, System Architecture

Sources: [README.md:1-20](https://github.com/antoinezambelli/forge/blob/main/README.md)

System Architecture

Related topics: WorkflowRunner and Agentic Loop

Sources: [CONTRIBUTING.md](https://github.com/antoinezambelli/forge/blob/main/CONTRIBUTING.md)

Module Structure and API

Related topics: System Architecture, WorkflowRunner and Agentic Loop

Sources: [src/forge/__init__.py]()

AI Context Pack and portable assets

After deciding to continue, take the project context into your own AI host.

Complete pack plus user-owned assets

These files are planning and verification assets for Claude Code, Codex, Gemini, Cursor, ChatGPT, and other AI hosts.

Download complete pack Read Human Manual

BundleComplete Project Pack AssetAI Context Pack AssetBoundary & Risk Card AssetHuman Manual AssetPitfall Log AssetPrompt Preview AssetQuick Start ManifestPROJECT_PACK.json

Preflight checks

Treat this page as a planning asset, not proof that your local environment is ready.

The manual is generated from source-linked project files and Doramagic validation signals.
Community evidence warnings stay visible instead of being converted into marketing claims.
This English page is indexable because the locale quality gate passed and explicit English index approval is enabled.
Use the upstream repository as the final authority for installation commands, license, and version-specific behavior.