TrueFoundry 开源 Agent 运行时 TrueForge
1/ TrueFoundry, whose AI Gateway sits under production LLM traffic for Fortune 5…
做 Agent 工程的同学值得关注，TrueForge 是 MIT 许可的完整运行时，带人工审批和沙箱执行，可直接落地对比成本，建议拉取源码试跑。
1/ TrueFoundry, whose AI Gateway sits under production LLM traffic for Fortune 500 companies across healthcare, pharma, financial services and gaming, just open-sourced their agent harness!
1/ TrueFoundry，其AI网关承载着财富500强公司在医疗保健、制药、金融服务和游戏领域的生产级LLM流量，刚刚开源了他们的智能体框架！
TrueForge by TrueFoundry went live on GitHub today. Open Source (MIT License), Vendor-Neutral. That is the permissive kind, with no usage clauses, no commercial restrictions, no community edition with the good parts removed!
TrueFoundry的TrueForge今天在GitHub上正式上线。开源（MIT许可证），厂商中立。这是宽松型许可证，没有使用条款限制，没有商业限制，没有移除精华部分的社区版！
You can fork it, run it commercially, and ship it inside your own product.
你可以自由分叉它，商业运行它，并将其集成到自己的产品中。
There are two ways to run it. Local mode runs as a single process with SQLite and no extra infrastructure, intended for personal use on your own machine. Hosted mode runs through Docker Compose or Helm with Postgres and Redis, built for teams and production deployments. The agent features are identical in both modes; only the infrastructure around the server changes.
有两种运行方式。本地模式作为单进程运行，使用SQLite，无需额外基础设施，适合个人在自有机器上使用。托管模式通过Docker Compose或Helm运行，使用Postgres和Redis，专为团队和生产部署设计。两种模式下的智能体功能完全相同；仅服务器周围的基础设施有所不同。
What you get is an agent harness, the runtime that turns a model into something you can leave running in production.
你获得的是一个智能体框架，即运行时环境，能将模型转化为可在生产中持续运行的系统。
Tool orchestration, context management, subagents, human approval checkpoints, sandboxed code execution, and turn-by-turn traces of everything the agent did.
工具编排、上下文管理、子智能体、人工审批检查点、沙箱代码执行，以及智能体每一步操作的逐步追踪记录。
TrueForge matched the accuracy of Claude Managed Agents on Opus 4.8, at ~30% lower cost on the same model, and up to ~75% lower when the same work was routed to GLM-5.2.
TrueForge在Opus 4.8上达到了与Claude托管智能体相当的准确性，在相同模型上成本降低约30%，当相同工作路由到GLM-5.2时，成本降低高达约75%。
A thread on what @truefoundry just shipped 🧵:
关于@truefoundry刚刚发布内容的帖子🧵：
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力