dsh-mojibake-interceptor
Mojibake interceptor for DeepSeek Harness: feature-based garbled-text detection that interrupts garbled writes and asks for review (an identical retry passes).
254 results
Mojibake interceptor for DeepSeek Harness: feature-based garbled-text detection that interrupts garbled writes and asks for review (an identical retry passes).
记忆搬家:把 Claude / ChatGPT / Claude Code 的历史记忆搬进 DeepSeek Harness —— 带逐字证据,逐条批准 | Move your Claude & ChatGPT memory into DeepSeek Harness (DSH), with verbatim evidence and one-by-one approval
Agent-decided approvals for DeepSeek Harness: a workspace-write base permission mode where an independent approval subagent judges every sandbox escalation (risky operations are rejected), with a configurable approval model and a per-session audit trail in the conversation window's 审批 tab.
pi-tui based interactive terminal front door for DeepSeek Harness agents
Native KaleidoSphere database-analysis tools for DeepSeek Harness
DSH 本地知识库管理插件:多格式导入、智能分块、向量索引、混合检索、rerank、快照、kbpack 迁移(设计见 DESIGN.md v2.1)
DeepSeek Harness 喜马拉雅播客插件:Host 端代理喜马拉雅搜索/专辑/曲目/收藏声音/订阅专辑/关注主播接口并解析播放地址(免费曲直链 + 登录态 baseInfo 解锁已购/VIP 内容),支持订阅/收藏/关注云端写回(与手机 App 同步),浏览器侧提供播放条与搜索/专辑/主播/我的面板,并注册 ximalaya_play 模型工具
Join the Muretai agent network from DeepSeek Harness: own identity, invite-based introductions, signed end-to-end encrypted agent-to-agent messaging, inbound-mail wake.
LLM-as-a-Verifier plugin for DeepSeek Harness: fine-grained logprob-based scoring, pairwise pivot tournaments (best-of-N) and an automatic end-of-turn quality gate.
Session KB for DeepSeek Harness: full-text search across all past sessions and recall them as @references. 会话库:全文搜索历史会话,一键以 @引用 召回给 AI(session search / recall / knowledge base).
Unified ModelID routing for DeepSeek Harness: one logical model id over multiple providers, first-token failover with cooldown, health-aware ranking, fallback reasoning efforts, purpose-based simple/complex task split, per-tier reasoning effort, and a settings-page management panel.
WeChat Official Account content studio for DeepSeek Harness: anti-homogenization writing methodology, blessing-image visual baseline, gpt-image cover pipeline with OCR acceptance, interaction rules, and the measured xiaolvshu (newspic) draft web API.
DSH AI 代码安全审查插件:secure_scan/secure_diff/secure_fix_verify/secure_report/secure_export/secure_baseline/secure_deps/secure_policy_show/secure_policy_set 九工具,40+ 确定性规则、密钥熵检测、git diff/staged 审查、SARIF 导出、基线接受与 SBOM-lite,零运行时依赖。
A graph-based task management system with CLI and web UI for atomic, verifiable tasks
DSH plugin: official-model Honcho v3 memory plus a perspective-safe shared knowledge base
DSH plugin for semantic code search via Milvus vector database
Agent governance suite for DeepSeek Harness (enterprise companion): policy-based tool gating (allow/deny/ask), structured JSONL audit trail, and per-agent token quotas against the host token meter — state under $DSH_HOME/gov
Developer quick-reference toolbox for DeepSeek Harness (DSH): 12 themed categories (195 entries) + zero-dependency dev tools (regex tester, JSON format, timestamp, Base64/URL codec, cron generator, line diff). 开发者速查工具箱。
Shared Claw/session policy schema, preset bases, MCP init defaults. Does not deny tools. 策略契约:schema / 预设基类 / MCP 初始化默认,不执行拦截。
理解任何东西技能包(移植自 Understand-Anything)
DeepSeek Harness plugin: Lord/Serf agent protocol 0.5 skills (file-based multi-agent orchestration with bounded execution and schema-validated submissions)
Evidence-driven company and job intelligence plugin for DeepSeek Harness.
Vanilla DSH in the terminal: a Web-GUI-parity Cordis surface over dsh-base (Unofficial Community Plugin). Your plugins, presets, tools, and settings — nothing extra, nothing less.
DSH LLM response-stream injection/pollution filter: hard-block rare Unicode scripts (Track A) and score-based disposal of control chars / protocol markers / script mixing / spam keywords (Track B) on the llm/stream waterfall.