AI 工具AI TOOLS· CHAT-AGENT
Helicone/helicone
给大模型应用做监控和日志的开源工具,改一行代码就能用。Open-source observability for LLM apps: change your base URL to log every call and reach many models.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
改两个设置就能记录全部AI 模型请求
打开面板回看每次请求详情
用同一个入口调用上百种AI 模型
搭建一套自己用的监控平台
Log every call just by pointing to a different URL.
See dashboards of your request history and cost.
Compare many models in one place.
Self-host the service using Docker.
Test changes and review outputs in the dashboard.
上手GET STARTED
git clone https://github.com/Helicone/helicone.git选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01读取 API KeyReads an API keyreadme
apiKey: process.env.HELICONE_API_KEY,
静态扫描发现一处中风险:代码从环境变量读取 API Key(apiKey: process.env.HELICONE_API_KEY),这是常见做法,但需注意密钥不要硬编码或泄露。未发现高风险项。仅核验官方页面,未审计服务端代码;数据处理和费用以官网为准。A static scan found a medium-level note about reading an API key from the environment variable HELICONE_API_KEY. That is a normal pattern for this kind of tool, but it means you should review how your keys are handled before deploying.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+1.5%+1.5%
6.2k → 6.3k stars · 49 个快照6.2k → 6.3k stars · 49 snapshots
讨论DISCUSSION
1 SOURCES1 SOURCES
2 条外部提及2 external mentions
状态STATUS
持续活跃Active
质量 AQuality A
改一行 baseURL 就能把 OpenAI 等调用日志记到 Helicone,仪表盘里直接看,试用门槛很低。Backed by YC W23 and launched on Hacker News with 166 points.
HN_STORY · 166 points · 72 comments
HN_STORY · 5 points · 0 comments
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude/"
},
{
"agent": "cursor",
"evidence": "tree: .cursor/"
}
],
"apiKey": "ai\", apiKey: process.env.HELICONE_API_KEY, }); const response = await clie",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 10,
"dev-tools": 1,
"indie-web": 0,
"skill-agent": 0,
"productivity": 0
},
"primary": "ai-tools",
"secondary": "chat-agent"
},
"localRuntime": "| | Ollama",
"skillMdTotal": 0,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 4,
"agent": 0,
"media": 0,
"design": 1,
"browser": 0,
"devtool": 1,
"security": 0,
"marketing": 1,
"productivity": 0
},
"classification": [
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme"
],
"skillMdFetched": 0
}