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

罗磊的独立博客
Y
Y Combinator Blog
Recent Announcements
Recent Announcements
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
V
Visual Studio Blog
MyScale Blog
MyScale Blog
M
MIT News - Artificial intelligence
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
T
The Blog of Author Tim Ferriss
Martin Fowler
Martin Fowler
博客园 - 【当耐特】
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
宝玉的分享
宝玉的分享
Engineering at Meta
Engineering at Meta
WordPress大学
WordPress大学
Google DeepMind News
Google DeepMind News
C
Check Point Blog
Last Week in AI
Last Week in AI
F
Fortinet All Blogs
博客园 - 聂微东
Blog — PlanetScale
Blog — PlanetScale
H
Help Net Security
GbyAI
GbyAI
云风的 BLOG
云风的 BLOG

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 - joedaviesio/tirith: Cost observability for Claud...
2026-04-16 · via Hacker News - Newest: "AI"

Video launch

https://www.youtube.com/shorts/uZCAqzqLfi4

Go Reference License: MIT Release

AI API cost observability — one import, full transparency.

Tirith is a local CLI + transparent proxy that logs every AI API call with cost, tokens, latency, and custom tags. Add one import line to your app — nothing else changes.

Quickstart (30 seconds)

Install the binary, then pick the column that matches your stack:

shell · terminal

brew install joedaviesio/homebrew-tap/tirith
Anthropic · Proxy Anthropic · Python SDK Anthropic · TypeScript SDK OpenAI · Python SDK

shell · ~/.zshrc

export ANTHROPIC_BASE_URL=\
  http://localhost:5555/proxy/anthropic

shell · terminal

curl $ANTHROPIC_BASE_URL/v1/messages \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{...}'

shell · terminal

pip install tirith-sdk anthropic

python · app.py

import tirith
import anthropic

shell · terminal

npm install tirith-sdk @anthropic-ai/sdk

typescript · app.ts

import "tirith-sdk";
import Anthropic from "@anthropic-ai/sdk";

shell · terminal

pip install tirith-sdk openai

python · app.py

import tirith
from openai import OpenAI

Once your code is wired up, start the proxy and run your app:

shell · terminal

tirith start       # proxy on :5555, dashboard on :5556

Then view your spend:

shell · terminal

tirith report
open http://localhost:5556    # dashboard

Integration Paths

Pick whichever fits your workflow — all three do the same thing:

Path How When to use
SDK wrapper import tirith (Python) / import "tirith-sdk" (TS) Recommended — zero config, auto-patches clients at import
CLI wrapper tirith run -- python app.py Ad-hoc runs without touching code
Manual env var export ANTHROPIC_BASE_URL=http://localhost:5555/proxy/anthropic Anything that reads *_BASE_URL

Supported Providers

Provider Proxy Python SDK TypeScript SDK
Anthropic
OpenAI 🚧 planned ✅ (patches client) 🚧 planned
Google 🚧 planned 🚧 planned 🚧 planned

Tagging Calls

Attribute spend to features, users, or environments via headers:

X-Tirith-Tag          # feature tag (e.g., "grant-scanner")
X-Tirith-User         # user attribution
X-Tirith-Session      # session grouping
X-Tirith-Environment  # production, staging, dev

Privacy

  • Prompts and responses are never logged — metadata only.
  • API keys pass through the proxy; Tirith never stores them.
  • All data stays local in ~/.tirith/data.db (SQLite).

Configuration

  • Proxy port: 5555 (configurable via tirith start --port)
  • Dashboard port: 5556
  • Config file: ~/.tirith/config.yaml
  • Data file: ~/.tirith/data.db

Contributing

See CONTRIBUTING.md for build instructions and PR guidelines. Security issues: see SECURITY.md.

License

MIT — see LICENSE.