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

Bifrost
Bifrost

huggingface/safeagents

Safely run your agents using any coding harness

Visit GitHub
Python
79
2
2 contributors
Apache License 2.0
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

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

Momentum

How fast huggingface/safeagents 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

Oct 29 – Nov 5, 2026

Stars +39 in 8 days

0510
9

Forks +2 in 8 days

01
1

Merged PRs 16 in 8 days

0510
9

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

Not in the Trendshift top 25 in this period

Oct 29Oct 30Oct 31Nov 1Nov 2Nov 3Nov 4Nov 5
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
Thu, Oct 29, 2026+0+19
Fri, Oct 30, 2026+9+16
Sat, Oct 31, 2026+6+00
Sun, Nov 1, 2026+3+00
Mon, Nov 2, 2026+3+00
Tue, Nov 3, 2026+2+00
Wed, Nov 4, 2026+9+01
Thu, Nov 5, 2026+7+00
Total+39+216
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Nov 31 post
    • Hugging Face's safeagents blocks a tool call when its scanner finds something rated high, or when the call goes to a host only the model has mentioned. Medium findings just get logged unless you set…

      Read full on X, posted by @metehanariman

      @metehanariman · x.com

  2. Nov 11 post
    • The safety check moved inside the agent. Oct 29–31: Hugging Face open-sourced safeagents — a local proxy between the coding harness and the model server. Every tool call is inspected before the shell…

      Read full on X, posted by @Archive2050

      @Archive2050 · x.com

  3. Oct 301 post
    • We benchmarked models on that task: catching reward hacking, sandbox escape, harness introspection, credential misuse The challenge is catching dangerous calls without blocking legitimate work, and…

      Read full on X, posted by @yb2698

      @yb2698 · x.com

You might also like

Repositories close to huggingface/safeagents
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

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

SumonMSelim/agentguard

Shell

Universal security guardrails and workflow policies for AI coding agents.

5411

agent-chaperone/agent-chaperone

TypeScript

Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.

228

sondera-ai/sondera-coding-agent-hooks

Rust

Hooking implementations and supporting tools for various coding agents (Claude, Cursor, Gemini, etc)

23133

leepokai/jev-guard

JavaScript

Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, checks skills and plugins. Claude Code, Codex, Copilot, Gemini, Cursor, pi, OpenCode, ACP.

14525

DobermanCore/Doberman-Core

Python

Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.

27754

LuD1161/agentjail

Go

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

1008

Srajangpt1/ai-security-crew

Python

Security for AI coding agents, covering the code they write and the actions they take. MCP server, skills and a runtime guard.

7327

safedep/gryph

Go

Security layer for AI coding agents. Works with Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, Pi Agent and more.

18325

liwala/sandshell

Shell

sandbox, guardrails, and audit across your coding agents

29