@akslcw/dsh-negative-ledger
Agent negative-knowledge ledger for DeepSeek Harness: records failed paths with evidence hashes and retry conditions, auto-invalidates on evidence change.
163 results
Agent negative-knowledge ledger for DeepSeek Harness: records failed paths with evidence hashes and retry conditions, auto-invalidates on evidence change.
Observe-only hash-chained evidence receipts for DeepSeek Harness
Adaptive Context Plane core bundle: Evidence Ledger + Governance + Context Composer + User Model (explicit)
Evidence-driven mathematical modeling and verification skills for DeepSeek Harness
Native continuity recovery for long-running DeepSeek Harness agents
Host-level vision bridge for text-only models: analyze_image tool (Ollama local / Xiaomi MiMo cloud / any OpenAI-compatible endpoint) returning structured evidence.
Reproducible deterministic benchmark evidence for DSH tools and plugins
Policy-enforced, evidence-first governed workflows for DeepSeek Harness agents — installable community plugin (governance core + authority provider)
Evidence-first 2Origin state projection, diff and immutable freeze for DeepSeek Harness
Galgame Doctor for DeepSeek Harness: multi-release translation memory, reviewer CSV queues, evidence plans, strict QA, and rollback.
Eyes for text-only DeepSeek on DeepSeek Harness: image understanding via Antigravity IDE quota (default, flash/pro), OpenAI-compatible VLM endpoints, Gemini API, or local Ollama — model-invokable vision tool, wrapper adapters for deepseek/opencode-go, evidence memory, and a polished client panel.
Evidence-first model control plane for DeepSeek Harness
Reliable todo panel for DSH: survives restarts, verifies completion evidence
Captain 控制台:面向求职公司筛查的可恢复、多智能体 DSH 工作流。
Content-addressed data and action lineage evidence for DeepSeek Harness
Runtime-first Debug Mode plugin for DeepSeek Harness
Evidence-driven system architecture reconnaissance for DeepSeek Harness
Bounded, read-only design evidence for agent harnesses; compatible with DeepSeek Harness and the Figma REST API.
Completion evidence gate for DeepSeek Harness goal-mode subagents
Content-addressed readiness proof for sanitized DeepSeek Harness observations on managed Windows hosts
Native memory for DeepSeek Harness — auditable facts with evidence chains, powered by StateCore
Codex-inspired planning, evidence, goal, and anti-loop policy plugin for DeepSeek Harness.
Citation extraction and evidence verification for DeepSeek Harness
Read-only recovery drill evidence for DeepSeek Harness