@dsh-external/dsh-evolution-console
Creator-native candidate capture, isolated evaluation, promotion, rollback, and visual lineage for DeepSeek Harness
88 results
Creator-native candidate capture, isolated evaluation, promotion, rollback, and visual lineage for DeepSeek Harness
Reflect2Evolve memory plugin: layered L1/L2/L3 memory, reflection-weighted value backprop, cross-task policy induction, skill crystallization, and three-tier retrieval for OpenClaw, Hermes Agent, and DeepSeek Harness.
LLM 评估:输出质量评估、幻觉检测、基准测试、回归守护。受 wshobson/agents(38k★ MIT)启发。
Kimi WebBridge host plugin for DeepSeek Harness: model tools that drive the user's REAL browser (navigate, snapshot, click, fill, evaluate, screenshot, network inspection, tab management) through the local kimi-webbridge daemon
DSH-native multi-runtime baseline, ablation, and reproducible evaluation control plane
Paired experiments and promotion gates for DSH plugins.
Controlled A/B comparisons and evidence-backed reports for DeepSeek Harness plugins and presets.
Kimi WebBridge for DeepSeek Harness: drive the user's real browser (navigate, click, fill, snapshot, screenshot, evaluate, network, upload, PDF) through the local Kimi WebBridge daemon
A blind, fair, local Agent arena inside DSH Web: same task, same commit, isolated worktrees, shared verification, judge before you reveal.
Natural project teaching and first-delivery verification guidance using native DSH instructions.
DSH-native persistent memory and safe session-aware retrieval plugin.
Evidence packaging, Skill evaluation, and controlled trajectory comparison for DeepSeek Harness sessions
Independent community DeepSeek Harness plugin for secure multi-file upload, native images, local document retrieval, and coordinate-aware text/PDF/DOCX/XLSX/PPTX reading.
Evidence-governed experience memory for DeepSeek Harness
Codex-style lossless-retrieval context manager for the DeepSeek Harness: token-budgeted sliding window, persistent working notes, and cold-history search over the append-only session log
Research lab for DeepSeek Harness: AutoSci-style wiki (experiments/literature/decisions), ASI-Bench-grade eval rigor ledger, arXiv digest, adversarial paper review, and academic writing checks.