开发者工具11 hours ago
Self-operated inference at the market floor on TokenGO
开源LLM和视频模型的OpenAI兼容API
bingus-bongo · HN
Use GLM-5.3 in Cursor today via tokengo API
完整作品展
技术栈
60 projects
开源LLM和视频模型的OpenAI兼容API
bingus-bongo · HN
Use GLM-5.3 in Cursor today via tokengo API
自学习AI平台，通过用户反馈持续改进。
thomasconway01 · HN
Conw.ai – Independent local AI platform and developer API
AI agents 构建您的 API 集成，当其发生故障时自动修复。
@getselfheal · X
SelfHeal - integrations that fix themselves. Vendor changes their API at 2am? The agent rewrites the connector, tests it, redeploys. You sleep. Demo (it breaks + heals on camera):
使用AI引导的冥想课程、日记和模式检测工具来探索意识和自我觉醒。
@SamirS58890 · X
world's suffering
统一云平台，集数据库、AI推理、函数、容器和存储于一体。
kiran-ravi · HN
Scalix World – AI native Neo cloud built by two engineers in Rust
为人类和AI代理记录和检索决策，追踪完整来源。
@burn2delete · X
多智能体LLM系统的可视化编辑器，支持本地推理。
sascha10000 · HN
Multi-agent LLM editor with local inference via WebSockets
在推理时为 AI 代理注入工程化认知能力。
@frank_brsrk · X
reasoning tools for ai agents
AI代理的运行时安全网关，在执行前检查并批准所有操作。
@chlorosagent · X
— a security gate for AI agents that checks every action before it fires, so a bad instruction can't make your agent send money, delete data, or do anything you can't undo.
Runpod是无服务器GPU推理平台，冷启动低于200ms，按秒计费。
@svpino · X
You can check out Runpod here: Thanks to the Runpod team for partnering with me on this post.
对比和评估 AI 模型在编码、推理、代理和其他基准测试中的表现。
davidtsong · HN
Benchmarklist: track AI benchmarks (2.4k+), models, and capabilities
