Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

Busbar
Busbar
Bifrost
Bifrost
Omnigraph
Omnigraph
OfinTech Desk
OfinTech Desk
It's a plan
It's a plan

antoinezambelli/forge

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

Visit GitHub
Python
2.3k
203
7 contributors
MIT License
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Busbar

Control what AI can do before it acts

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

OfinTech Desk

An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

It's a plan

Open-source Linear alternative

An issue tracker where AI agents take the work you assign them

Momentum

How fast antoinezambelli/forge is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 21 – Nov 20, 2026

Stars +31 in 61 days

012
2

Forks +26 in 61 days

0510
9

Merged PRs 8 in 61 days

0123
3

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 21Sep 29Oct 7Oct 15Oct 23Oct 31Nov 8Nov 16
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Mon, Sep 21, 2026+1+00
Tue, Sep 22, 2026+1+00
Wed, Sep 23, 2026+1+00
Thu, Sep 24, 2026+0+00
Fri, Sep 25, 2026+1+00
Sat, Sep 26, 2026+0+00
Sun, Sep 27, 2026+0+00
Mon, Sep 28, 2026+0+00
Tue, Sep 29, 2026+0+00
Wed, Sep 30, 2026+1+00
Thu, Oct 1, 2026+0+00
Fri, Oct 2, 2026+0+00
Sat, Oct 3, 2026+0+00
Sun, Oct 4, 2026+1+00
Mon, Oct 5, 2026+0+00
Tue, Oct 6, 2026+0+00
Wed, Oct 7, 2026+2+00
Thu, Oct 8, 2026+0+00
Fri, Oct 9, 2026+1+00
Sat, Oct 10, 2026+1+00
Sun, Oct 11, 2026+0+00
Mon, Oct 12, 2026+1+00
Tue, Oct 13, 2026+2+00
Wed, Oct 14, 2026+0+00
Thu, Oct 15, 2026+0+12
Fri, Oct 16, 2026+1+20
Sat, Oct 17, 2026+0+90
Sun, Oct 18, 2026+0+50
Mon, Oct 19, 2026+2+60
Tue, Oct 20, 2026+1+10
Wed, Oct 21, 2026+1+00
Thu, Oct 22, 2026+0+00
Fri, Oct 23, 2026+1+11
Sat, Oct 24, 2026+0+01
Sun, Oct 25, 2026+0+00
Mon, Oct 26, 2026+1+00
Tue, Oct 27, 2026+2+00
Wed, Oct 28, 2026+1+00
Thu, Oct 29, 2026+0+00
Fri, Oct 30, 2026+0+10
Sat, Oct 31, 2026+0+00
Sun, Nov 1, 2026+0+00
Mon, Nov 2, 2026+1+03
Tue, Nov 3, 2026+0+00
Wed, Nov 4, 2026+2+00
Thu, Nov 5, 2026+0+00
Fri, Nov 6, 2026+1+00
Sat, Nov 7, 2026+1+00
Sun, Nov 8, 2026+0+00
Mon, Nov 9, 2026+0+00
Tue, Nov 10, 2026+1+00
Wed, Nov 11, 2026+1+00
Thu, Nov 12, 2026+0+01
Fri, Nov 13, 2026+0+00
Sat, Nov 14, 2026+1+00
Sun, Nov 15, 2026+0+00
Mon, Nov 16, 2026+0+00
Tue, Nov 17, 2026+0+00
Wed, Nov 18, 2026+0+00
Thu, Nov 19, 2026+0+00
Fri, Nov 20, 2026+0+00
Total+31+268
  • 1#1 on the list
  • 7Rank that day
  • Not trending
5
  • GitHub trending history

    Where the repository ranked on GitHub Trending, one dot for each day it was on a list

    May 21, 2026Best #12

    #1#5#10#15#20#25
    Top 10
    May 21, 2026
    The left and right arrow keys step from day to day; Home and End go to the first and the last

    Mentions and achievements

    Where people are talking about antoinezambelli/forge, and every badge it has earned
    1. Nov 101 post
      • The honest reality check: • Error recovery was 0% across ALL models without retry nudges. • Serving backend matters: the SAME Mistral 12B weights scored 7% on llama-server vs 83% on Llamafile. •…

        Read full on X, posted by @0xFevertime

        @0xFevertime · x.com

    2. 3 months earlier
    3. Aug 161 post
      • It's been a big couple of weeks for open-source models - I'm pretty stoked about this one. Inkling Small (264B-A12B), DeepSeek V4 Flash 0731 (284B-A13B), Muse Glimmer 30B and Qwen3.8-27B. A lot of…

        Read full on X, posted by @AntoineZambelli

        @AntoineZambelli · x.com

    4. 12 days earlier
    5. Aug 41 post
      • Unlock reliable LLM workflows with @antoinezambelli/forge See link below 👇

        Read full on X, posted by @RepoGems

        @RepoGems · x.com

    6. 2 months earlier
    7. Jun 121 post
      • Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks What this means: → Biggest AI news today → Implications for the industry → Why you should care

        Read full on X, posted by @The_neural_post

        @The_neural_post · x.com

    8. 8 days earlier
    9. Jun 41 post
      • An open, locally-runnable model just reached frontier tier on my agentic tool-calling eval. Qwen3.6-35B-A3B (Q4, llama.cpp, native FC) reforged: 94.8%. Claude Haiku 4.5 reforged: 94.5%. Statistical…

        Read full on X, posted by @AntoineZambelli

        @AntoineZambelli · x.com

    10. Jun 21 post
      • Forge took an 8B model from 53% to 99% on agentic tasks using structured guardrails. Not fine-tuning, not RLHF — just smart constraints. Sometimes the biggest lever isn't a bigger model. It's better…

        Read full on X, posted by @azarnoush

        @azarnoush · x.com

    11. Jun 11 post
      • Nearly 2,000 devs starred Forge, a Python framework for self-hosted LLM agents with full tool-calling. No API key. No cloud. Works with llama-cpp and llamafile. Your data stays local. #Python #llm…

        Read full on X, posted by @fireawesome26

        @fireawesome26 · x.com

    12. 7 days earlier
    13. May 251 post
      • Top tools this week (May 19 – May 25): 1/ Forge — MIT Python framework where layered guardrails take an 8B model from 53% to 99% on agentic benchmarks. Solo author, 1.8k stars in three months

        Read full on X, posted by @prodimpossible

        @prodimpossible · x.com

    14. May 222 posts
      • An 8B local model beat Claude Sonnet. Not because it's smarter — because it had better infrastructure. Same weights: 7% on one backend, 83% on another. Forge proved the 76-point swing.

        Read full on X, posted by @OmarAlmoktar

        @OmarAlmoktar · x.com

      • Guardrails take an 8B model from 53% to 99% on agentic tasks. No model change, no new hardware. Just retry nudges, step enforcement, and error recovery stacked around the same model. Ministral 8B…

        Read full on X, posted by @so_sthbryan

        @so_sthbryan · x.com

    You might also like

    Repositories close to antoinezambelli/forge
    FeaturedAdvertise to 180K+ monthly visitors
    OfinTech Desk

    An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

    Busbar

    Control what AI can do before it acts

    It's a plan

    Open-source Linear alternative

    An issue tracker where AI agents take the work you assign them

    Omnigraph

    Versioned graph database on object storage. Git-style workflows and multimodal retrieval

    Bifrost

    Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

    miquido/draive

    Python

    All-in-one Python framework for building production-ready LLM agents and workflows. Developed by Miquido.

    11115

    InternLM/lagent

    Python

    A lightweight framework for building LLM-based agents

    2.3k270

    truefoundry/trueforge

    TypeScript

    The open-source agent harness - the runtime layer that turns an LLM into a working agent.

    6.5k600

    dreadnode/rigging

    Python

    Lightweight LLM Interaction Framework

    42639

    langroid/langroid

    Python

    Harness LLMs with Multi-Agent Programming

    4.2k457

    sherifkozman/the-llm-council

    Python

    A Claude Code framework for multi-llm planning and development agents

    9721

    Productive-Superintelligence/lllm

    Python

    A light-weight, modular, and high-performance framework for building llm agentic systems.

    9914

    Mirascope/mirascope

    Python

    The LLM Anti-Framework

    1.5k165

    Oaklight/ToolRegistry

    Python

    ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs (OpenAI, Anthropic, Gemini, MCP, OpenAPI, native Python)

    6812