Submit repository
Discover trends that matter
Trending repositories
Live mentions
Topics
GitHub trending
Repositories
Developers
Repository engagements
Insights
Stats
antoinezambelli/forge — GitHub trending stats & insights | Trendshift
Featured
Bindu
Openhuman
antoinezambelli/forge
#
AI agent
#
AI workflow
#
Local LLM
#
Self-hosted
A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows
Visit GitHub
Python
860
45
2 contributors
last commit 19 days ago
last user commit 19 days ago
MIT License
created 3 months ago
Social mentions
Recent discussions about this repository across the web
the real bottleneck for agentic AI isn't model size — it's reliability. forge just showed guardrails can push an 8B local model from 53% to 99% on structured tasks. stop chasing 100B parameters and…
@mrluiscalderon · x.com · 17 minutes ago
The funniest AI trend right now is: people making frameworks just to babysit local models 😭 Forge basically adds: - retries - guardrails - rescue parsing - workflow enforcement - synthetic tools As…
@varun_slops · x.com · about 2 hours ago
Most agent tooling targets frontier models. Forge targets 8B on local GPU. Rescue parsing for bad tool calls. Step enforcement. VRAM budgets. 86.5% eval score. Ministral 8B Q8. → 952 stars. Ollama,…
@agentxagi · x.com · about 2 hours ago
Forge: 8B model just matched what required 70B before. rules beat raw power.
@Ferbin08 · x.com · about 4 hours ago
Forge tool boosts local AI models, enabling smaller solutions to hold their ground. A big win for decentralized AI.
@TheAlibAi · x.com · about 5 hours ago
Forge 证明了一个道理:8B 小模型加上好的 guardrails,agentic 任务准确率从 53% 飙到 99%。与其卷参数量,不如卷系统设计。 #AI #LLM #Agentic
@Suchuanyi · x.com · about 6 hours ago
Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks (
@betterhn300 · x.com · about 6 hours ago
Forge boost: an 8B LLM with guardrails jumps from 53% to 99% success on agentic tasks. Open-source safety layers pay off.
@zoltansoon · x.com · about 7 hours ago
Forge shows that adding simple guardrails can lift an 8B model from 53% to 99% on agentic benchmarks, highlighting the power of lightweight safety layers.
@zoltansoon · x.com · about 7 hours ago
Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks (
@betterhn50 · x.com · about 12 hours ago
Load more
No trending activity
This repository has not yet been featured on GitHub Trending
Repository activities
repository's daily and monthly activities across stars, forks, merged PRs, issues, and closed issues