与「Filesystem」相关的搜索结果

Introducing Mirage, a unified virtual filesystem for AI agents! 6 weeks. 1.1M+ lines of code. We rewrote bash from the ground up so cat, grep, head, and pipes work across heterogeneous services. S3, Google Drive, Slack, Gmail, GitHub, Linear, Notion, Postgres, MongoDB, SSH, and more, all mounted side-by-side as one filesystem. Bash that AI agents already know works on every format! cat, grep, head, and wc parse .parquet, .csv, .json, .h5, even .wav! One pipe can stitch S3, Drive, GitHub, Slack, and Linear together, same Unix semantics throughout. Workspaces are versioned too. Snapshot, clone, and roll back the whole thing with one API call. A two-layer cache turns repeated reads into local lookups, so agent loops stay fast and cheap. Drop a Workspace into FastAPI, Express, or a browser app. Wire it into OpenAI Agents SDK, Vercel AI SDK, LangChain, Mastra, or Pi. Run it alongside Claude Code and Codex. Site: GitHub: #AIAgents# #OpenSource# #AgenticAI# #Strukto# #Filesystem# #VFS#

Introducing AIO Sandbox, All-in-One Sandbox Environment for AI Agents. Unchecked AI autonomy is a ticking time bomb; it’s time to pull the plug on full system unfettered access. We can no longer afford to give AI agents the 'keys to the kingdom' without oversight. The 'wild west' of AI agents running with total system control is officially over. AIO Sandbox is an open-source project designed to solve these problems. It is everything your agent needs, out of the box. No more juggling multiple services. AIO Sandbox ships a complete, pre-wired environment in a single Docker container. The AIO (All-in-One) Sandbox is a containerized environment designed for both human developers and AI agents. Its architecture is built around a "Batteries-Included" philosophy, providing a full Linux desktop-like environment inside a single Docker container. Unified Environment: One Docker container with shared filesystem. Files downloaded in the browser are instantly accessible in Terminal and VSCode. Out of the Box: Built‑in VNC browser, VS Code, Jupyter, file manager, and terminal—accessible directly via API/SDK. Agent-Ready: Pre-configured MCP Server with Browser, File, Terminal, Markdown, Ready-to-use for AI agents. Developer Friendly: Cloud-based VSCode with persistent terminals, intelligent port forwarding, and instant frontend/backend previews. Secure Execution: Isolated Python and Node.js sandboxes. Safe code execution without system risks. Production Ready: Enterprise-grade Docker deployment. Lightweight, scalable. Calling all AI agent developers! How are you securing your builds? Let’s try running your agent in AIO Sandbox and compare notes. AIO Sandbox is open-sourced under the Apache License 2.0. Contributions welcome. GitHub: Official website: #OpenSource# #AIAgent# #Docker#

The latest release of OpenClaw is the first one that ships with our new TypeScript security hardening file-system lib. Previously, this was a grown mess of ad-hoc hardening which was hard to maintain, slow and inconsistent. increased some file ops by 10x.

看到很多朋友问过一个问题，为什么给我的 Claude Code 安排任务，它都不会一口气执行完，而是跑最多几十分钟就停下来，然后问我要不要继续。例如让它把项目中的单测全部补全（大概 1k 个），它跑了大概 200 个就停下来了。 cc 并不是对一句话任务抗拒，如果不理解它的执行机制，很难设计出能跑长程任务的 harness 流程。 在执行一个超大任务的时候，单 agent 的执行流程大概是这样的：1）刚开始是高效模式，指令遵循效果特别棒；2）跑了大概 80k tokens 的时候，context 开始逼近 compact 阈值；3）紧接着，对话历史被压缩为摘要，模型开始忘记刚才修复单测的细节；4）再经过一两轮 auto-compact，它甚至会开始重复检查已修复的测试，当触发 maxTurns 并且 response 没有 ToolUse 指令时，模型会退出任务，然后开始询问用户："我已经修复了约 200 个测试，要继续吗？" 如果你在当前 session，回复继续，接下来的工作，它会做的更加不符合预期，并且退出得更快。 任何试图在一个 agent session 内完成海量工作的方案，最终都会碰到 context 膨胀 → compact → 信息丢失 → 效率下降的问题。 其实优化方向也特别简单，设计一个主-子 Agent 的运行模式（任务调度器），同时将任务进度写到 file system 中（进度持久化），每个子 agent 有独立 context、独立退出逻辑，主 agent 只负责调度和进度追踪，从而绕过单一 agent 的所有瓶颈。 因此给 cc 的指令需要包含至少这三部分： 1）任务分解。不要给一个无边界的指令（如修复所有单测），而是先扫描出所有失败测试，按目录或模块分组，每组 15-30 个，作为一个独立子任务。关键是每个子任务的 prompt 必须自包含——写清楚文件路径、错误现象、期望行为，不能写"根据之前的分析来修复"，因为子 agent 看不到父 agent 的历史。 2）进度持久化。在项目根目录维护一个 progress.json，记录 completed / failed / pending 三个列表。主 agent 每轮调度前读这个文件决定下一批任务，子 agent 完成后更新对应条目。这样即使主 agent 自己被 compact，重读文件就能恢复全部状态。 3）失败策略。子 agent 报错时，如果错误可修复，用 SendMessage 继续同一个子 agent（保留错误上下文更高效）；如果方向完全错了，启动新的子 agent 避免锚定在错误路径上；多次失败则上报用户，不要无限重试烧 token。 Claude Code 其实已经内建了这套能力。最直接的方式是启用 Coordinator Mode（输入 /coordinator），主 agent 自动变成纯调度者：它不执行任何实际工具调用，只负责理解子 agent 的返回结果、合成下一步的具体指令、并行派发独立任务；而每个子 agent 会通过 AgentTool 启动，它们有独立 context。 记住一句话就行了：设计多个 agents，各司其职、快进快出，把进度交给文件系统来记忆。

This is Farzapedia. I had an LLM take 2,500 entries from my diary, Apple Notes, and some iMessage convos to create a personal Wikipedia for me. It made 400 detailed articles for my friends, my startups, research areas, and even my favorite animes and their impact on me complete with backlinks. But, this Wiki was not built for me! I built it for my agent! The structure of the wiki files and how it's all backlinked is very easily crawlable by any agent + makes it a truly useful knowledge base. I can spin up Claude Code on the wiki and starting at index.md (a catalog of all my articles) the agent does a really good job at drilling into the specific pages on my wiki it needs context on when I have a query. For example, when trying to cook up a new landing page I may ask: "I'm trying to design this landing page for a new idea I have. Please look into the images and films that inspired me recently and give me ideas for new copy and aesthetics". In my diary I kept track of everything from: learnings, people, inspo, interesting links, images. So the agent reads my wiki and pulls up my "Philosophy" articles from notes on a Studio Ghibli documentary, "Competitor" articles with YC companies whose landing pages I screenshotted, and pics of 1970s Beatles merch I saved years ago. And it delivers a great answer. I built a similar system to this a year ago with RAG but it was ass. A knowledge base that lets an agent find what it needs via a file system it actually understands just works better. The most magical thing now is as I add new things to my wiki (articles, images of inspo, meeting notes) the system will likely update 2-3 different articles where it feels that context belongs, or, just creates a new article. It's like this super genius librarian for your brain that's always filing stuff for your perfectly and also let's you easily query the knowledge for tasks useful to you (ex. design, product, writing, etc) and it never gets tired. I might spend next week productizing this, if that's of interest to you DM me + tell me your usecase!