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
Websitebench
Websitebench
Omnigraph
Omnigraph
Busbar
Busbar

ifixai-ai/iFixAi

Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.

#LLM evaluation
Visit GitHub
Python
45.8k
2k
8 contributors
Apache License 2.0
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

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

Websitebench

Can AI agents reverse-engineer real websites?

Omnigraph

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

Busbar

Control what AI can do before it acts

Momentum

How fast ifixai-ai/iFixAi 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 16 – Nov 15, 2026

Stars +30,770 in 61 days

01K2K3K
2,290

Forks +636 in 61 days

050100150
101

Merged PRs 283 in 61 days

0204060
43

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

Top 25 overall

1311412721024483

Top 25 in Python

572143818141412825122221911911217
Sep 16Sep 24Oct 2Oct 10Oct 18Oct 26Nov 3Nov 11
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 PRsAll languagesPython
Wed, Sep 16, 2026+185+41Not trendingNot trending
Thu, Sep 17, 2026+153+30Not trendingNot trending
Fri, Sep 18, 2026+202+81Not trendingNot trending
Sat, Sep 19, 2026+76+00Not trendingNot trending
Sun, Sep 20, 2026+26+00Not trendingNot trending
Mon, Sep 21, 2026+25+20Not trendingNot trending
Tue, Sep 22, 2026+23+10Not trendingNot trending
Wed, Sep 23, 2026+19+00Not trendingNot trending
Thu, Sep 24, 2026+10+02Not trendingNot trending
Fri, Sep 25, 2026+0+01Not trendingNot trending
Sat, Sep 26, 2026+0+00Not trendingNot trending
Sun, Sep 27, 2026+3+10Not trendingNot trending
Mon, Sep 28, 2026+618+70#13#5
Tue, Sep 29, 2026+334+70Not trending#7
Wed, Sep 30, 2026+702+141#11#2
Thu, Oct 1, 2026+1,087+712#4#1
Fri, Oct 2, 2026+688+106#12#4
Sat, Oct 3, 2026+887+90#7#3
Sun, Oct 4, 2026+319+142Not trendingNot trending
Mon, Oct 5, 2026+836+934Not trending#8
Tue, Oct 6, 2026+467+623Not trending#18
Wed, Oct 7, 2026+667+910Not trending#14
Thu, Oct 8, 2026+383+76Not trendingNot trending
Fri, Oct 9, 2026+319+510Not trendingNot trending
Sat, Oct 10, 2026+499+1321Not trending#14
Sun, Oct 11, 2026+321+321Not trendingNot trending
Mon, Oct 12, 2026+347+313Not trendingNot trending
Tue, Oct 13, 2026+1,878+2222#2#1
Wed, Oct 14, 2026+1,278+387#10#2
Thu, Oct 15, 2026+1,011+341#24#8
Fri, Oct 16, 2026+397+210Not trendingNot trending
Sat, Oct 17, 2026+393+380Not trendingNot trending
Sun, Oct 18, 2026+418+350Not trendingNot trending
Mon, Oct 19, 2026+539+450Not trendingNot trending
Tue, Oct 20, 2026+558+60Not trending#25
Wed, Oct 21, 2026+814+241Not trending#12
Thu, Oct 22, 2026+1,689+10143#4#2
Fri, Oct 23, 2026+576+40Not trending#22
Sat, Oct 24, 2026+298+91Not trendingNot trending
Sun, Oct 25, 2026+373+60Not trendingNot trending
Mon, Oct 26, 2026+641+90Not trending#19
Tue, Oct 27, 2026+892+50Not trending#11
Wed, Oct 28, 2026+1,116+60Not trending#9
Thu, Oct 29, 2026+819+70Not trending#11
Fri, Oct 30, 2026+1,265+153#8#2
Sat, Oct 31, 2026+2,290+170#3#1
Sun, Nov 1, 2026+1,054+80Not trending#7
Mon, Nov 2, 2026+524+617Not trendingNot trending
Tue, Nov 3, 2026+167+20Not trendingNot trending
Wed, Nov 4, 2026+216+20Not trendingNot trending
Thu, Nov 5, 2026+138+30Not trendingNot trending
Fri, Nov 6, 2026+74+40Not trendingNot trending
Sat, Nov 7, 2026+259+08Not trendingNot trending
Sun, Nov 8, 2026+159+40Not trendingNot trending
Mon, Nov 9, 2026+244+115Not trendingNot trending
Tue, Nov 10, 2026+253+20Not trendingNot trending
Wed, Nov 11, 2026+267+00Not trendingNot trending
Thu, Nov 12, 2026+261+21Not trendingNot trending
Fri, Nov 13, 2026+186+30Not trendingNot trending
Sat, Nov 14, 2026+248+10Not trendingNot trending
Sun, Nov 15, 2026+279+140Not trendingNot trending
Total+30,770+636283
  • 1#1 on the list
  • 7Rank that day
  • Not trending
4
  • GitHub trending history

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

    Oct 14, 2026Best #7

    #1#5#10#15#20#25
    Top 10
    Oct 2026Nov
    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 ifixai-ai/iFixAi, and every badge it has earned
    1. Nov 141 post
      • 想检查自己的智能体是不是按设定的职责做事,可以看 iFixAi。 它会在模拟场景里向智能体发请求,再用另一个模型当评审,把问了什么、它做了什么记下来。 先有演示流程,不配密钥也能看一遍;正式评审要自己接模型和接口。

        Read full on X, posted by @zjian66666

        @zjian66666 · x.com

    2. Nov 91 post
      • 10 open-source LLM observability and eval tools to explore for your own setup. A shortlist ranked by GitHub stars—not a quality benchmark. Repos below.

        Read full on X, posted by @AsWill11

        @AsWill11 · x.com

    3. Nov 81 post
      • The no-key demo scored Grade A, 100%, ten passes, in two seconds. Their own control check then skipped that fixture. iFixAi audits whether an agent does the job it was given. 44.0K stars, Apache-2.0.…

        Read full on X, posted by @naveendas96

        @naveendas96 · x.com

    4. Nov 21 post
      • Monday stack check: 10 GitHub repos your agents will thank you for: vercel-labs/agent-desktop - reliable computer use for any agent, sees real UI structure karpathy/nanochat - the best ChatGPT $100…

        Read full on X, posted by @benou_irl

        @benou_irl · x.com

    5. 13 days earlier
    6. Oct 201 post
      • iFixAi 今天在 GitHub Trending 上涨了 2109 颗星,总数到了 27605。它只回答一个问题:这个 agent 是不是在做它该做的事?官方说不到 120 秒就能给出答案。 它有两种跑法,可以由人来跑,也可以让 agent 自己跑。 人来跑的时候,审计的人和被审的 agent 是两方,"独立"说得通。换成 agent 自己跑,发起审计的就是被审的那一方。项目的口号是…

        Read full on X, posted by @iluciddreaming

        @iluciddreaming · x.com

    7. Oct 171 post
      • 做 AI 应用,模型选好之后,还会遇到几个实际问题: 怎么查自己的资料?怎么记住以前的对话?用什么界面操作?出了问题怎么检查? 这 10 个 GitHub 项目,按用途整理好了: 一、知识库与长期记忆 1. LlamaIndex 连接自己的数据,搭建文档检索和问答应用。 2. RAGFlow 把文档整理成知识库,让 AI 找到相关资料后再回答。 3. Mem0 给 AI…

        Read full on X, posted by @bdall_1

        @bdall_1 · x.com

    8. Oct 161 post
      • ③ scientific-agent-skills(约 5 万星) 给 Agent 装上做科研的技能包,偏生物、化学、医药数据分析。 4/6

        Read full on X, posted by @DAIaf889

        @DAIaf889 · x.com

    9. Oct 153 posts
      • Most agent evals score latency, tokens, or prompt-injection resistance. They still miss the business question: is the agent doing the job your org actually hired it for? ifixai-ai/iFixAi, +1,887…

        Read full on X, posted by @DegenOfWallSt

        @DegenOfWallSt · x.com

      • Agent 说任务完成了,你敢直接信吗? iFixAi 会检查 Agent 的行为和结果,开源版能在自己的环境跑。 做自动化交付前,可以先让它找一次容易漏掉的问题。 报告仍要人看,别把一个分数当最终验收.

        Read full on X, posted by @Aoyi21

        @Aoyi21 · x.com

      • AI 审计 AI,120 秒出结果。 iFixAi:独立审计你的智能体到底有没有在干正事,人类可以跑,智能体自己也能跑。 #AI #开源

        Read full on X, posted by @ieddysun

        @ieddysun · x.com

    You might also like

    Repositories close to ifixai-ai/iFixAi
    FeaturedAdvertise to 180K+ monthly visitors
    Omnigraph

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

    Websitebench

    Can AI agents reverse-engineer real websites?

    Busbar

    Control what AI can do before it acts

    Bifrost

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

    microsoft/scope

    TypeScript

    Scope | Agentic Experience evaluation platform (Research preview)

    8733

    Hona/openeval

    TypeScript

    Typed prompt-and-judge SDK, CLI, and evidence viewer for agent evaluations

    791

    AgentX-ai/AgentX-Trace-Eval

    TypeScript

    The trust layer for your AI agent on any platform. Trace and evaluate your agent. Full Observability. Run Model portability analysis. Autotune your agent.

    855

    kayba-ai/Kyoko

    Python

    🔨 Kyoko is the all-in-one, fully local tool for debugging and improving your AI agents.

    10010

    awslabs/uaef

    Python

    Universal Agent Evaluation Framework (UAEF) is a framework-agnostic evaluation system for AI agents. Invoke any agent and score it on multiple metrics spanning tool calling, response quality, safety, performance, and reasoning. Track experiments against baselines, catch regressions automatically, and get LLM-generated insights.

    1158

    dodoguardai/dodoguard

    TypeScript

    DodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for Dify, Coze, FastGPT, n8n, Tencent ADP, ByteDance HiAgent, and more.

    2751

    LambdaTest/rook

    Shell

    rook by TestMu AI: Agent Assurance from the terminal. Test how your AI agents actually behave across workflows, tools, and actions, and catch failures and vulnerabilities before they ship.

    8116

    ai-evals-course/evals-skills

    Skills that guide AI coding agents to help you build product-specific AI evals.

    1.8k130

    alibaba/skill-up

    Go

    An evaluation and evolution tool for Agent Skills.

    1.5k138