{
  "added_at": "2026-10-19",
  "additional_evidence_urls": [
    "https://github.com/openbin-ai/binny/blob/000b6aca8c9d266b38252470102ac16c98575cd8/main.go",
    "https://github.com/openbin-ai/binny/blob/000b6aca8c9d266b38252470102ac16c98575cd8/internal/auth/auth.go",
    "https://github.com/openbin-ai/binny/blob/000b6aca8c9d266b38252470102ac16c98575cd8/internal/ghidra/ghidra.go",
    "https://github.com/openbin-ai/binny/blob/000b6aca8c9d266b38252470102ac16c98575cd8/internal/sandbox/sandbox.go",
    "https://github.com/openbin-ai/binny/blob/000b6aca8c9d266b38252470102ac16c98575cd8/.github/workflows/release.yml",
    "https://github.com/openbin-ai/binny/blob/000b6aca8c9d266b38252470102ac16c98575cd8/LICENSE",
    "https://github.com/openbin-ai/binny/blob/000b6aca8c9d266b38252470102ac16c98575cd8/CLA.md",
    "https://github.com/openbin-ai/binny/releases/tag/v0.1.0-beta.2"
  ],
  "category": "agent-workflows",
  "description_en": "An open-source terminal agent harness from OpenBin that runs a user-chosen hosted or local model over binary-analysis data. It reads decompiled functions, strings, imports and data from an OpenBin or OpenAPK project or a local Ghidra container run, follows triage, investigation and drafting playbooks, and saves a draft malware-analysis or vulnerability-research report for human review. It is an analysis harness with draft outputs, not a reconstruction project.",
  "description_zh": "OpenBin 推出的开源终端智能体框架，让使用者自选的托管或本地模型处理二进制分析数据。它从 OpenBin 或 OpenAPK 项目、或本地 Ghidra 容器的分析结果中读取反编译函数、字符串、导入表和数据，按分诊、调查与起草流程工作，并保存恶意软件分析或漏洞研究报告草稿供人工审阅。它是输出草稿的分析框架，而非重建项目。",
  "entry_url": "https://awesomerea.org/resources/binny-agent-harness/",
  "entry_url_zh": "https://awesomerea.org/zh/resources/binny-agent-harness/",
  "evidence_url": "https://github.com/openbin-ai/binny/blob/000b6aca8c9d266b38252470102ac16c98575cd8/README.md",
  "group": "agents",
  "id": "binny-agent-harness",
  "json_url": "https://awesomerea.org/resources/binny-agent-harness/record.json",
  "kind": "integration",
  "markdown_url": "https://awesomerea.org/resources/binny-agent-harness/index.md",
  "markdown_url_zh": "https://awesomerea.org/zh/resources/binny-agent-harness/index.md",
  "name": "BINNY",
  "name_zh": "BINNY 逆向分析智能体框架",
  "record_type": "resource",
  "relationship": "independent-agent-integration",
  "requirements": [
    "The reviewed pin follows the v0.1.0-beta.2 release of 2026-10-15. BINNY is a Go terminal program; release builds use Go 1.22 and cover Linux, macOS and Windows, and the README installers fetch scripts from openbin.ai. Startup needs an OpenBin sign-in: main.go loads the openbin CLI’s stored credentials and stops with an instruction to run openbin login when none exist. Source comments describe planned paid access whose gating is deferred during testing.",
    "Models are bring-your-own-key, with Anthropic, OpenAI, DeepSeek, Qwen, Kimi, Gemini through an OpenAI-compatible endpoint and Bedrock preconfigured; Ollama or LM Studio models must support tool calling and need a larger context window than Ollama’s 4k default. Analysis data comes from the user’s OpenBin or OpenAPK projects or a local file. Local decompilation and the sandbox need Docker, and the first local decompile downloads an OpenBin Ghidra worker image of about 700 MB.",
    "The sandbox tool runs scripts in a container with no network, a read-only root and sample mount, dropped capabilities and CPU, memory and process limits. Triage labels samples with the STIX 2.1 malware vocabulary, malware and vulnerability modes change the report lens, and autonomous, supervised or collaborative modes decide when the agent stops to ask. The README treats existing reports as claims to check and saves drafts for review before publication.",
    "The repository has Go unit tests, which the release workflow runs before cross-compiling; it publishes no benchmark, accuracy measurement or worked example report. Its README still calls the source repository private while it is public.",
    "LICENSE is AGPL-3.0; the README states AGPL-3.0 or later. Contributors sign a CLA so OpenBin can also offer the code under a commercial licence, and the README says the OpenBin platform it talks to uses the same licence. Model services, OpenBin accounts, Ghidra and analysed samples carry their own terms."
  ],
  "requirements_zh": [
    "所审阅的固定版本位于 2026-10-15 发布的 v0.1.0-beta.2 之后。BINNY 是 Go 编写的终端程序；发布构建使用 Go 1.22，覆盖 Linux、macOS 与 Windows，README 中的安装命令从 openbin.ai 获取脚本。启动需要登录 OpenBin：main.go 读取 openbin 命令行工具保存的凭据，若不存在则停止并提示运行 openbin login。源码注释称计划采用付费访问，测试期间暂缓收费限制。",
    "模型需自备密钥，预置 Anthropic、OpenAI、DeepSeek、Qwen、Kimi、经 OpenAI 兼容接口接入的 Gemini 以及 Bedrock；Ollama 或 LM Studio 本地模型须支持工具调用，且上下文窗口需大于 Ollama 默认的 4k。分析数据来自使用者的 OpenBin 或 OpenAPK 项目或本地文件。本地反编译与沙箱需要 Docker，首次本地反编译会下载约 700 MB 的 OpenBin Ghidra 工作镜像。",
    "沙箱工具在容器中运行脚本：无网络、根文件系统与样本挂载均为只读、移除全部权能，并限制 CPU、内存和进程数。分诊按 STIX 2.1 恶意软件词表标注样本，恶意软件与漏洞两种模式切换报告视角，自主、监督与协作模式决定智能体何时停下询问。README 将已有报告视为待核实的主张，并把草稿保存待审阅后再发布。",
    "仓库包含 Go 单元测试，发布工作流会在交叉编译前运行；仓库未公开基准、准确性测量或完整示例报告。其 README 仍称源码仓库为私有，而该仓库实际公开。",
    "LICENSE 为 AGPL-3.0，README 表述为 AGPL-3.0 或更高版本。贡献者需签署 CLA，使 OpenBin 也能以商业许可提供代码；README 称其连接的 OpenBin 平台采用相同许可。模型服务、OpenBin 账户、Ghidra 与被分析样本各有条款。"
  ],
  "targets": [
    "app",
    "binary",
    "firmware"
  ],
  "url": "https://github.com/openbin-ai/binny",
  "verification": "source-reviewed",
  "verified_at": "2026-10-18"
}