惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

月光博客
月光博客
雷峰网
雷峰网
S
SegmentFault 最新的问题
博客园 - 【当耐特】
博客园_首页
量子位
爱范儿
爱范儿
博客园 - 叶小钗
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
Jina AI
Jina AI
V
V2EX
美团技术团队
V
Visual Studio Blog
博客园 - 三生石上(FineUI控件)
IT之家
IT之家
Hugging Face - Blog
Hugging Face - Blog
Apple Machine Learning Research
Apple Machine Learning Research
小众软件
小众软件
博客园 - 聂微东
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
The Cloudflare Blog
宝玉的分享
宝玉的分享
WordPress大学
WordPress大学
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
GitHub - manojbajaj95/authsome: Local auth cli for AI age...
pkhodiyar · 2026-04-28 · via Hacker News - Newest: "AI"

PyPI version Python 3.13+ License: MIT PyPI downloads Tests codecov

              __  __
  ____ ___  _/ /_/ /_  _________  ____ ___  ___
 / __ `/ / / / __/ __ \/ ___/ __ \/ __ `__ \/ _ \
/ /_/ / /_/ / /_/ / / (__  ) /_/ / / / / / /  __/
\__,_/\__,_/\__/_/ /_/____/\____/_/ /_/ /_/\___/

Local auth for AI agents.

Log in once via OAuth2/API Key. Authsome keeps the credentials fresh for every AI agent.


Why Agents Are Different

Agents need API access that survives outside an interactive app:

  • agents run without interactive sessions
  • tokens expire, rotate, and need refresh
  • tool access must work in scripts, cron, CI, SSH, background workers, and parallel pipelines

Hardcoded env tokens leak or go stale. DIY auth means rebuilding flow logic, token storage, refresh handling, expiry checks, and per-provider config for every project.

Authsome is the local credential layer agents can call at runtime.

  • No credential sprawl. One encrypted store — every provider, every agent, one place.
  • No SaaS, no privacy trade-off. Credentials never leave your machine. No third-party cloud dependency.
  • No browser required at runtime. Setup can use browser PKCE, device code, or a browser bridge for secure API key entry. After that, agents run headlessly in CI, SSH, cron, workers, or parallel pipelines.

How It Works

The CLI is the agent's interface: setup once, then inject fresh credentials whenever a tool runs.

┌──────────┐        authsome         ┌──────────────┐
│  Agent   │ ──────────────────────▶ │ Local Vault  │
└──────────┘                         └──────┬───────┘
     ▲                                      │
     │       fresh token / API key          │ encrypted
     └──────────────────────────────────────┘

Authenticate once:

authsome login github

Then agents get valid credentials on demand:

authsome get github --field access_token --show-secret
# → ghu_...

authsome export github --format shell
# → export GITHUB_TOKEN=ghu_...

authsome run -- python my_agent.py
# runs behind a local auth proxy that injects headers at request time
# without exposing secrets in the child process environment.
# matched automatically via provider host_url (e.g. api.openai.com)

Credentials are stored locally, encrypted at rest, and refreshed before expiry. No server. No account. No cloud.


Why Authsome

authsome Hardcoded env tokens DIY
Automatic token refresh build it
OAuth2 + API keys build it
Runtime headless use varies
Local — no SaaS dependency
Built-in providers, zero config
Multi-account per provider build it

Authsome gives agents one command for a valid token, without scattering long-lived secrets across every project.


Quick Start

pip install authsome
authsome init
authsome login github                  # opens browser, completes PKCE flow
authsome login github --flow device_code  # headless: Device Code, works over SSH and CI
authsome login openai                  # secure API key entry via browser bridge
authsome list                          # all connections + token status

Docs

Specs

License

MIT — see LICENSE.