Enhanced prompt cache and sticky session management plugin for OpenCode, especially effective for AI API relay/gateway setups with stable SHA256-based cache keys.
Progressive tool discovery for DeepSeek Harness — tiny stable surface, searchable catalog, real pipeline execution, context cache intact.
An OpenCode plugin that hoards tiny project-context notes so agents read less and waste fewer tokens.
Diff-aware context-caching proxy for Llama 4 Scout (10M context): splits an immutable codebase snapshot from the live git diff to maximize LLM prefix-cache hits, exposed as an OpenAI-compatible API.
MCP server giving Claude Code long-context memory of a codebase through Gemini's 1M-token window: one workspace scan, implicit caching by default, explicit Context Cache on request (125 s → 14 s measured on repeat queries), agentic file access for larger repos.
To associate your repository with the context-cache topic, visit your repo's landing page and select "manage topics."