flameox
jWright6359/flameoxRuntime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.
TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.
Time-shifting task delegation for DeepSeek Harness (dsh): plan tasks at leisure, they run unattended off-peak, come back to a report. Human-adjudicated, desktop + web.
DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.
DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.
Codex architect and read-only reviewer for DeepSeek Harness Desktop. ChatGPT sign-in, model selection, explicit file approval and checkpoints. Preview.
Audio-reactive turn rail for DeepSeek Harness: the transcript's own turn marks dance to whatever the system is playing (WASAPI loopback), with hover-only highlighting and a left/right rail option.
DeepSeek Harness plugin: connects the codebase-memory-mcp code graph, nudges the model at the decision point, corrects failed MCP calls, and indexes repositories by itself.
TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.
Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.
Normify · DSH 插件:把项目架构写成归一化的分形模块树,三层校验(写时 / 校验 / 冻结回执)、30 个 normify_* 工具 + normify-gen 技能,一键渲染单文件交互式架构图;支持伴随式开发(change_open → brief → check → 实施 → refresh → change_close)。
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.
专门为 agent 打造的开源 agent 搜索工具,具备 200+的搜索源及多语言搜索能力,覆盖中文/英文/学术/代码/购物/金融/新闻/百科。
Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.
Normify · DSH 插件:把项目架构写成归一化的分形模块树,三层校验(写时 / 校验 / 冻结回执)、30 个 normify_* 工具 + normify-gen 技能,一键渲染单文件交互式架构图;支持伴随式开发(change_open → brief → check → 实施 → refresh → change_close)。
DSH plugin — free OpenCode Zen models for DeepSeek Harness (DSH). Free LLM API, no API key needed. 在 DSH 中使用 OpenCode Zen 免费模型,无需 API key
收尾自检哨兵:任务收尾时强制「全面检查 → 修复 → 再全面检查」循环,自动跑测试/lint/audit,有未修复的问题就打回,直到连续三轮零问题才判定完成并通知用户。
跨代自评估进化插件:配置仓库(版本化资源+锚点链)、热重载(.agent-presets 运行时应用/回滚)、子智能体白纸继承配置跑 modeltest 评测、账本(分数/轨迹/失败模式)。受益主体为宿主 agent 本体。
仓库尚未提供可用的公开描述。
红队渗透辅助插件:侦察/枚举/指纹/CVE 匹配/敏感路径(8 工具,仅限授权测试)
Noema long-term memory plugin for DSH: durable, inspectable agent memory with recall tools and a settings page.
A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.
Backup tooling for DeepSeek Harness session data: bundle + sha256 integrity verification + spot-restore loader check.