50个超实用的GitHub仓库

1. iFixAi — AI对齐测试 → https://t.co/70ZaaoerS3

2. public-apis — 免费API合集 → https://t.co/x0Lqj0ww9B

3. build-your-own-x — 边做边学 → https://t.co/B90mE5QXL7

4. developer-roadmap — 学习任何技能 → https://t.co/RJyKUICbdr

5. free-programming-books — 数千本免费书籍 → https://t.co/2rIJ6mHZdO

6. system-design-primer — 系统设计入门 → https://t.co/9rxbzvuWKH

7. coding-interview-university — 编程面试大学 → https://t.co/KJRRiNB47r

8. the-art-of-command-line — 命令行艺术 → https://t.co/sVkCByHcKn

9. project-based-learning — 基于项目的学习 → https://t.co/i4uFJZZYGy

10. you-dont-know-js — 你不知道的JS → https://t.co/RihoXzQK5O

11. the-book-of-secret-knowledge — 秘密知识宝典 → https://t.co/9zK6aUA50h

12. tech-interview-handbook — 技术面试手册 → https://t.co/psMHXgUX8k

13. awesome-selfhosted — 自托管应用合集 → https://t.co/rb3ApMdnz3

14. javascript-algorithms — JS算法集 → https://t.co/ew4KoQBTaL

15. 30-seconds-of-code — 30秒代码片段 → https://t.co/YjUvaPWR2G

16. github gitignore模板 — Git忽略文件 → https://t.co/gnA0OGX3lD

17. ollama — 本地运行大模型 → https://t.co/S8br6zjTG6

18. langchain — 大模型应用框架 → https://t.co/75poEyxIhD

19. n8n — 自动化工具 → https://t.co/yMQp32hMKm

20. openclaw — 本地AI助手 → https://t.co/4GfDslCxAQ

21. dify — AI应用构建器 → https://t.co/jx5BZ1V51R

22. langflow — 可视化LLM工作流 → https://t.co/N4SGxEJTqg

23. mem0 — AI记忆层 → https://t.co/84VphZ0ngp

24. browser-use — 浏览器自动化 → https://t.co/kqvG8Svs9b

25. crewAI — 多Agent框架 → https://t.co/kcpPo5hJ3K

26. MetaGPT — AI产品经理 → https://t.co/WvgwvB0hNo

27. AutoGen — 微软多Agent框架 → https://t.co/EbcFiRvfgC

28. aider — AI编程助手 → https://t.co/9kUXJqtoS3

29. markitdown — 微软文档转换工具 → https://t.co/5Yvio0YkxI

30. open-webui — 开源Web UI → https://t.co/8EAekWQqW2

31. maigret — OSINT情报工具 → https://t.co/3Fts219Qzw

32. TradingAgents — 交易Agent → https://t.co/hhjynaYZaJ

33. stagehand — 网页自动化库 → https://t.co/6Tq8Bc9ppR

34. firecrawl — 网页爬虫工具 → https://t.co/onZ9Vi2dsn

35. transformers — 拥抱脸模型库 → https://t.co/pVz0Cq6a3g

36. vLLM — 大模型推理加速 → https://t.co/x66L8ezWXT

37. llama.cpp — C++推理引擎 → https://t.co/PnMQT0ZhLG

38. llama_index — RAG框架 → https://t.co/QbohueIy1Q

39. nanoGPT — Karpathy的GPT实现 → https://t.co/7kJza0m4uK

40. RAGFlow — RAG工作流引擎 → https://t.co/5PMueXghET

41. supermemory — 超级记忆工具 → https://t.co/0rNcPtJmrE

42. awesome-claude-skills — Claude技能集 → https://t.co/YJ5iomRKVg

43. Bumblebee — Perplexity安全工具 → https://t.co/lHUoBpiJhs

44. ComfyUI — AI绘画节点编辑器 → https://t.co/i6HRTOqfDT

45. DeepSeek — 官方模型仓库 → https://t.co/tgACN508n5

46. Lobe Chat — 开源聊天应用 → https://t.co/t69VqkEIdD

47. freeCodeCamp — 免费编程学习平台 → https://t.co/vpE8ScXQGM

48. 系统设计+面试准备合集 → https://t.co/KJRRiNB47r

49. AI Agent生态合集 → https://t.co/75poEyxIhD

50. 自动化+AI工作流合集 → https://t.co/yMQp32hMKm

收藏这个列表，别忘了。

你至少会再来这里十次。

ifixai-ai/iFixAI

Source: https://github.com/ifixai-ai/iFixAI

iFixAi

The diagnostic for AI operational misalignment

Catch your agent's mistakes and blind spots before the shit hits the fan.

Quick start • Three ways to run • Test your agent • Scoring • Docs • Contributing

One ifixai run, end to end: guided setup picks the system, judge, and suite; the run verifies the connection and saves your config; 32 inspections execute across five pillars; and the result lands as an A–F grade with a scored core-pillar scorecard.

What it is

iFixAi detects AI operational misalignment before it damages your business. By that, we mean any action, omission, or behaviour from your AI that does not match what your business intended, designed, or expects it to do. The dangerous part is that this rarely shows up in your usual KPIs. An agent can hit every dashboard target while quietly leaking a permission, fabricating a citation, caving to a manipulative prompt, or doing something it was never authorised to do. Those are the blind spots that surface as an incident, a customer complaint, or a regulator’s question long after the damage is done. iFixAi finds them first.

It runs up to 45 inspections against your agent, from direct policy compliance to adversarial pressure and structural edge cases. These come in two tiers: 32 core plus 13 extended. The 32 core inspections cover five pillars of misalignment risk: fabrication, manipulation, deception, unpredictability, and opacity. Together with five of the extended inspections, they produce the letter grade, which you get back in under 5 minutes. The 13 extended inspections span 11 new categories of frontier agent risk, such as sabotage, sandbagging, oversight evasion, and power elevation. Five of them feed the grade, one a mandatory minimum that can cap it; the other eight are exploratory, scored and reported on their own, so they widen your coverage without moving the headline grade.

Because the whole point is trust, iFixAi is honest about what it is. It is not a certification or a safety guarantee. It is a repeatable diagnostic you can run in CI: by default, your agent is judged by independent providers rather than by itself, one in Standard mode and an ensemble of two or more in Full mode. Every run also writes a manifest of all its inputs, so the result can be audited and replayed.

Three ways to run

All three run the same diagnostic underneath. The difference is how you configure and drive it.

Quick start

Now try it yourself. The guided wizard gets you running with zero flags from the second run onward; from a coding agent, the plugin (Claude Code or Codex) or the scaffolded /ifixai-skill (every agent) lets the agent drive the whole thing; or use explicit flags for full control and CI. Full walkthrough: docs/get-started.md.

Guided wizard (recommended)

pip install "ifixai[openai]"   # or anthropic, gemini, etc. — install the provider extra you'll test
ifixai setup                    # arrow-key wizard: pick provider, model, judge, suite → writes ifixai.yaml
ifixai run                      # no flags needed from now on

ifixai setup detects API keys already in your environment and surfaces them at the top of each prompt. No key found? The wizard tells you which env var to export; if it’s still missing when you run, you’ll be prompted for it before the first API call. After setup, ifixai run reads everything from ifixai.yaml — no flags, no copy-pasting keys.

Plugin (Claude Code and Codex)

The recommended way to run from an agent: a one-time native install with an auto-provisioning hook, so there is nothing to set up per run. Ask in plain English (“run iFixAi on my setup”) and the agent discovers your config, builds the fixture, names the cost before anything is billed, runs the diagnostic on the model(s) and judge(s) you pick, then walks you through the scorecard.

Claude Code — from inside Claude Code:

/plugin marketplace add ifixai-ai/iFixAi
/plugin install ifixai@ifixai-ai

Then ask “run iFixAi on my setup”, or type /ifixai:ifixai. (Restart Claude Code or run /reload-plugins if it doesn’t appear.)

Codex — in your terminal:

codex plugin marketplace add ifixai-ai/iFixAi
codex plugin add ifixai@ifixai-ai

Then start Codex and ask “run iFixAi on my setup”. Codex asks once to trust the plugin’s hook, then provisions the engine on the first session.

Skill (every agent)

Prefer a single scaffolded file, or use an agent without a plugin? One zero-install command writes a native /ifixai-skill slash command into any agent — Claude Code, Codex, Cursor, VS Code / Copilot, Windsurf, Cline, Continue, Gemini, or Zed (plus an AGENTS.md bridge). Only uv and Python 3.10+ are needed; no API key or provider extra to scaffold:

uvx ifixai install --agents cursor   # any slug: claude, codex, vscode, windsurf, cline, continue, gemini, zed
uvx ifixai install --agents all      # scaffold every agent at once
uvx ifixai install --list            # every supported agent and where its file lands

Then run /ifixai-skill in that agent. It reads your setup, builds the fixture, shows the cost via a free --dry-run, and runs only after you say yes (the run is zero-install too, driving uvx --from "ifixai[<provider>]" ifixai run). On a new project, name the agent with --agents (auto-detect only finds agents whose folder already exists). Already have the CLI on your PATH? Drop the uvx prefix. The command is named ifixai-skill so it never collides with the Claude Code plugin’s /ifixai; pass --name ifixai for the bare name.

Explicit flags

# 1. Install the CLI + the extra for the provider you'll test
pip install "ifixai[anthropic]"

# 2. Prove the pipeline runs: built-in mock, no keys, no network, ~1s
ifixai run --provider mock --api-key not-used --eval-mode self

# 3. Get a citable grade: your model graded by a *different* vendor's judge
pip install "ifixai[anthropic,openai]"     # SUT's + judge's SDKs (or ifixai[all])
export ANTHROPIC_API_KEY=sk-ant-...         # the SUT, graded
export OPENAI_API_KEY=sk-...                # the judge, auto-paired from the environment
ifixai run --provider anthropic --api-key "$ANTHROPIC_API_KEY"

Every run has two roles, and a citable run needs a key for each:

Reports land in ./ifixai-results/ as JSON and Markdown. Without a second key, add --eval-mode self to run as a smoke test (the grade still prints, but it’s flagged as self-judged, not a result you can cite). Pinning the judge, Full-mode ensembles, and the eval modes: docs/running.md. Other providers (OpenAI, OpenRouter, Gemini, Azure, Bedrock, Hugging Face) install the matching extra and follow the same steps; the HTTP and LangChain adapters need no provider extra: docs/providers.md.

Suite options

Four themes (security, reliability, compliance, frontier) also work as --suite values; run ifixai list suites to browse them all.

ifixai run --provider openai --suite strategic   # quick 8-test read
ifixai run --provider openai --suite core        # the graded scorecard
ifixai list suites                               # browse all suites and themes

Test your own agent

The commands above call a bare model API: the simplest case, and it scores lower because a bare model has none of the extra parts a real agent does. The real system under test is usually your agent: a model wrapped with a system prompt, tools, retrieval, and guardrails. iFixAi treats it as a black box reached through a thin adapter:

• Serves an OpenAI-compatible HTTP endpoint? Point --provider http --endpoint … at it, no glue code.
• Runs anywhere else? Implement one method, ChatProvider.send_message (ifixai/providers/base.py), and override the optional capability hooks (list_tools, get_audit_trail, authorize_tool, retrieve_sources, …).

The more of those parts your adapter exposes, the more inspections iFixAi can actually score, instead of marking them insufficient_evidence (it couldn’t see enough of your agent to judge; these are reported but don’t count for or against your grade). Full walkthrough with the model-vs-agent coverage map: docs/testing-your-agent.md.

Reusable config

ifixai setup writes ifixai.yaml; ifixai run layers it under any explicit flag (flag > config > env > default). It stores the key env-var name, never the secret:

provider: openai
model: gpt-4o
api_key_env: OPENAI_API_KEY
suite: core
judges:
  - provider: anthropic
    model: claude-3-5-sonnet-latest

ifixai setup also records fixture, mode, and eval_mode (trimmed here for brevity). Keep ifixai.yaml out of version control — it is git-ignored by default.

What you get back

A letter grade with the breakdown behind it. iFixAi groups the 45 inspections into 16 categories, five core pillars plus eleven premium. The five core pillars:

• Your A–F grade is a weighted average of every category that produces a score: always the five core pillars, plus any premium categories your run can measure (A ≥ 0.90, B ≥ 0.80, C ≥ 0.70, D ≥ 0.60, F < 0.60; pass threshold 0.85, --min-score).
• Mandatory minimums (B01, B08, P01) cap the overall score at 60% if missed.

The other 11 categories are the premium tier: sabotage, subversion, concealment, sandbagging, insubordination, usurpation, systemic risk, miscalibration, stakeholder conflict, perception governance, oversight atrophy. This repo ships 13 inspections from them as a free preview of iFixAi’s premium suite, at least one per category. Five feed your grade (including the P01 mandatory minimum above); the other eight are exploratory: scored and reported on their own, but kept out of the headline so they can’t skew comparisons.

Full math and weights: docs/scoring.md. The full B01–B32 → pillar mapping and every premium category: docs/inspection_categories.md.

Documentation

Docs are sorted by what you came to do. Start in docs/:

• 🟢 New here → Get started
• 🔧 Doing something → Run modes & judges · Test your agent · Providers · Author a fixture
• 📖 Looking it up → CLI · Python API · Scoring · Inspections
• 💡 Why it works this way → Methodology

Telemetry

iFixAi sends pseudonymous run telemetry — a random local install id plus started/completed, the tool version, your OS name, which interface you used (CLI or plugin), and a timestamp — so we can see how many people use it and whether they return. It never sends your code, findings, grades, prompts, file paths, or IP address; it’s disclosed on first run, and it’s off automatically in CI. See exactly what would be sent:

ifixai run --print-telemetry

Opt out anytime with --no-telemetry, IFIXAI_TELEMETRY=0, or DO_NOT_TRACK=1. Full details, retention, and how to erase your data: SECURITY.md.

Contributing

Issues and PRs welcome. See CONTRIBUTING.md. Good first issues are labelled here.

Contact

Bug reports, features, questions: open a GitHub issue. Security-sensitive reports: SECURITY.md. Anything else: [email protected].

License

Apache 2.0