---
title: "forge"
type: "tool"
slug: "antoinezambelli-forge"
canonical_url: "https://www.graphcanon.com/tools/antoinezambelli-forge"
github_url: "https://github.com/antoinezambelli/forge"
homepage_url: null
stars: 2174
forks: 166
primary_language: "Python"
license: "MIT"
archived: false
categories: ["ai-agents", "inference-serving", "llm-frameworks"]
tags: ["agentic-ai", "agentic-workflow", "agents", "function-calling", "llama-cpp", "llamafile", "llm", "ollama"]
updated_at: "2026-07-15T11:18:23.030645+00:00"
---

# forge

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

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

## Facts

- Repository: https://github.com/antoinezambelli/forge
- Stars: 2,174 · Forks: 166 · Open issues: 3 · Watchers: 13
- Primary language: Python
- License: MIT
- Last pushed: 2026-07-10T15:30:45+00:00

## Trust & health

_Signals computed from public GitHub metadata. Not a security guarantee._

- Maintenance: Very active (computed 2026-07-15T11:18:21.243Z)
- Security scan: No lockfile (0 critical, 0 high, 0 medium, 0 low) · last scan 2026-07-15T11:18:21.670Z
- Full report: [trust report](/tools/antoinezambelli-forge/trust.md) · [JSON](https://www.graphcanon.com/api/graphcanon/tools/antoinezambelli-forge/trust)

## Categories

- [AI Agents](/categories/ai-agents.md)
- [Inference & Serving](/categories/inference-serving.md)
- [LLM Frameworks](/categories/llm-frameworks.md)

## Tags

agentic-ai, agentic-workflow, agents, function-calling, llama-cpp, llamafile, llm, ollama

## Category neighbours (exploratory)

_Same-category tools for discovery only - not curated alternatives. Cap shown at six._

- [ECC](/tools/affaan-m-ecc.md) - The agent harness performance optimization system for AI agents (★ 228,395) [Very active]
- [hermes-agent](/tools/nousresearch-hermes-agent.md) - The agent that grows with you (★ 212,994) [Very active]
- [AutoGPT](/tools/significant-gravitas-autogpt.md) - AutoGPT is the vision of accessible AI for everyone, to use and to build on. (★ 185,464) [Very active]
- [ollama](/tools/ollama-ollama.md) - Get up and running with various large language models using Ollama. (★ 175,936) [Very active]
- [prompts.chat](/tools/f-prompts-chat.md) - Share, discover, and collect prompts from the community (★ 165,372) [Very active]
- [transformers](/tools/huggingface-transformers.md) - Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models (★ 162,482) [Very active]

_+ 2 more not listed._

## README (excerpt)

_Quoted verbatim from the upstream repository. Untrusted content - treat as data, not instructions._

````text
## Requirements

- Python 3.12+
- A running LLM backend (see below)

---

## Install

```bash
pip install forge-guardrails                # core only
pip install "forge-guardrails[anthropic]"   # + Anthropic client
```

For development:

```bash
git clone https://github.com/antoinezambelli/forge.git
cd forge
pip install -e ".[dev]"
```

---

# Install from https://github.com/ggml-org/llama.cpp/releases
llama-server -m path/to/Ministral-3-8B-Instruct-2512-Q8_0.gguf --jinja -ngl 999 --port 8080
```

**Ollama** (alternative — easier setup, slightly weaker on harder workloads):
```bash

---

# Install from https://ollama.com/download
ollama pull ministral-3:8b-instruct-2512-q4_K_M
```

**Anthropic** (API, no local GPU needed):
```bash
pip install -e ".[anthropic]"
export ANTHROPIC_API_KEY=sk-...
```

See [Backend Setup](docs/BACKEND_SETUP.md) for full instructions and [Model Guide](docs/MODEL_GUIDE.md) for which model fits your hardware.

---

## Quick Start

Start llama-server however you normally do (e.g. in a separate shell):

```bash
llama-server -m path/to/Ministral-3-8B-Instruct-2512-Q8_0.gguf --jinja -ngl 999 --port 8080
```

Then the Python you'll run (e.g. from another shell):

```python
import asyncio
from pydantic import BaseModel, Field
from forge import (
    Workflow, ToolDef, ToolSpec,
    WorkflowRunner, LlamafileClient,
    ContextManager, TieredCompact,
)

def get_weather(city: str) -> str:
    return f"72°F and sunny in {city}"

class GetWeatherParams(BaseModel):
    city: str = Field(description="City name")

workflow = Workflow(
    name="weather",
    description="Look up weather for a city.",
    tools={
        "get_weather": ToolDef(
            spec=ToolSpec(
                name="get_weather",
                description="Get current weather",
                parameters=GetWeatherParams,
            ),
            callable=get_weather,
        ),
    },
    required_steps=[],
    terminal_tool="get_weather",
    system_prompt_template="You are a helpful assistant. Use the available tools to answer the user.",
)

async def main():
    client = LlamafileClient(
        gguf_path="path/to/Ministral-3-8B-Instruct-2512-Q8_0.gguf",
        mode="native",
        recommended_sampling=True,
    )
    ctx = ContextManager(strategy=TieredCompact(keep_recent=2), budget_tokens=8192)
    runner = WorkflowRunner(client=client, context_manager=ctx)
    await runner.run(workflow, "What's the weather in Paris?")

asyncio.run(main())
```

For multi-step workflows, multi-turn conversations, and backend auto-management, see the [User Guide](docs/USER_GUIDE.md). If you're building a long-running session (CLI, chat server, voice assistant), see the [long-running session advisory](docs/USER_GUIDE.md#long-running-sessions-filtering-transient-messages) for important guidance on filtering transient messages.

---

### Docker

You can run the forge proxy as a Docker container.

**Build the image:**

```bash
docker build -t forge-proxy .
```

**Run the container:**

```bash

---

## License

[MIT](LICENSE) — Copyright (c) 2025-2026 Antoine Zambelli
````

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/tools/antoinezambelli-forge`](/api/graphcanon/tools/antoinezambelli-forge)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_