frameevidence
Bounded, read-only design evidence for agent harnesses; compatible with DeepSeek Harness and the Figma REST API.
164 results
Bounded, read-only design evidence for agent harnesses; compatible with DeepSeek Harness and the Figma REST API.
OMV Audit Desk: an evidence-first vulnerability audit workbench for DeepSeek Harness
Native memory for DeepSeek Harness — auditable facts with evidence chains, powered by StateCore
Host-level vision bridge for text-only models: analyze_image tool (Ollama local / Xiaomi MiMo cloud / any OpenAI-compatible endpoint) returning structured evidence.
Codex-inspired planning, evidence, goal, and anti-loop policy plugin for DeepSeek Harness.
DSH standard vision skill: Qwen dynamic-resolution preprocessing + OpenAI-compatible VLM chain with failover/429 backoff, structured evidence mode, local tesseract-first long-screenshot OCR, paste-to-path (no framework patch). 8 tools + runtime skill.
Content-addressed readiness proof for sanitized DeepSeek Harness observations on managed Windows hosts
General APEX preset with a Minimal Pro anchor, role-bounded PTC implementation, verified handoffs, and evidence convergence
Citation extraction and evidence verification for DeepSeek Harness
Read-only recovery drill evidence for DeepSeek Harness
Evidence that CLI, MCP and GUI bindings reach the same DeepSeek Harness action core
Content-addressed, value-redacted policy drift evidence for DeepSeek Harness
Reproducible multi-source release evidence for DeepSeek Harness
Content-addressed audit indexes across independent DeepSeek Harness evidence producers
Drive9 workspace and durable evidence components for DeepSeek Harness
Content-addressed timeline, canon and character-knowledge evidence for DeepSeek Harness
Evidence-driven company and job intelligence plugin for DeepSeek Harness.
Evidence-first handoff auditing and documentation-sync skills for Codex and DeepSeek Harness.
Cordis-native, evidence-driven full-stack engineering discipline for DeepSeek Harness agents
Evidence-first long-term project memory for DeepSeek Harness
MindsEye: model-driven vision tools, structured evidence, and exact cache for DeepSeek Harness
Evidence-first frontier AI radar and reproducibility gate for DeepSeek Harness
Verification toolkit for DeepSeek Harness agents: evidence-based claim checking against workspace files with line citations, config file validation (JSON/YAML), HTTP URL status checks, npm package checks and GitHub repo submission-readiness checks — complementary to dsh-plugin-gate
Local-first vision for text-only DeepSeek Harness agents: route image understanding to a local OpenAI-compatible vision model, return structured JSON evidence (summary / OCR / layout / semantics / visual / uncertainty).