forge

Reliability layer for tool calling with self-hosted LLMs, offered as a proxy, a workflow runner and middleware.

IndexedMIT★ 2,262

Chalk Labs

Need help deploying forge?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

From the package registry. Read the repository before you give any tool access to your data.

pip install forge-guardrails

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Forge sits inside an agent loop and makes tool calls from a self-hosted model more reliable through rescue parsing, retry nudges and response validation. It runs as a proxy that OpenAI- and Anthropic-compatible clients can point at, as a WorkflowRunner that manages prompts, tool execution and context compaction, or as middleware inside your own loop. Backends include Ollama, llama-server, Llamafile, vLLM, generic OpenAI-compatible endpoints and Anthropic. The README states that Forge is not a multi-agent orchestrator.

Use cases: model-inference, agent-orchestration

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Languages: PythonREADME
Packages: forge-guardrails (pypi)README
Model providers: ollama, anthropic, openaiREADME
Maturity: Betagithub.com

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Alternatives

Frameworks for the same language with a similar way of orchestrating agents.

Signals

Stars: 2,262
Forks: 174
Open issues: 4
Weekly downloads: 92
Last commit: Oct 23, 2026 (7 days ago)
Last release: Aug 30, 2026 (2 months ago)
Last package publish: Aug 30, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Packages: pypi forge-guardrails
License: MIT
Repository: github.com/antoinezambelli/forge
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped: 50+; launches shipped
media placements: 500+; media placements
founders on every account: 2; founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get forge running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Need help deploying forge?

Call Get help

Cite this page

forge. Agent Mart. https://agentmart.dev/harnesses/forge (last updated 2026-10-24)