OpenCode package for Caveman: terse AI responses, slash commands, compact reviews, commit messages, and markdown memory compression.
-
Updated
Jun 18, 2026 - Python
#
token-saving
Here are 13 public repositories matching this topic...
ContextCore: An MCP server for Claude (or any AI tool) that enables massive token saving through hybrid search (BM25 + Embeddings)
python opencode embeddings cursor local-search clip cline cost-optimization rag hybrid-search ai-tools context-window llm-optimization claude-desktop mcp-server claude-tools token-saving
-
Updated
Jun 13, 2026 - Python
Local-first Trello cache with Git-style sync — built and optimised for AI agent workflows.
python cli trello trello-api automation sqlite cache developer-tools ai-agents local-first token-reduction round-trip-efficiency ai-agent-tools developer-tools-ai-agent token-saving
-
Updated
Mar 20, 2026 - Python
Project-agnostic dual-memory MCP CLI for Claude Code, Cursor, and OpenCode (Qdrant tuned hybrid retrieval + structural memory hooks)
-
Updated
Jun 11, 2026 - Python
Auto model-switching plugin for Claude Code — routes prompts to haiku/sonnet/opus (or any custom tier) to save API tokens
plugin hooks automation ai claude cost-optimization anthropic claude-code model-routing token-saving
-
Updated
Mar 23, 2026 - Python
Comet helps you save 15,000+ tokens! Comet is a TUI application that automatically generates descriptive git commit messages using local language models via Ollama or LMStudio or Openrouter. It analyzes your staged git diffs and provides a clean interface to review, edit, regenerate, and commit your changes instantly.
github git terminal vscode tui pipx tui-app llm openrouter ollama lmstudio antigravity claude-code token-saving token-saver
-
Updated
Jun 8, 2026 - Python
Zero-dependency Q&A cache for OpenClaw - SQLite-based, no Redis/Embedding API needed. Reduce token consumption with keyword matching + edit distance.
-
Updated
Apr 24, 2026 - Python
tokens openai-proxy token-reduction prompt-compression token-cost token-saving llm-cost-reduction agentic-middleware
-
Updated
Jun 29, 2026 - Python
Auto-trigger graphify knowledge-graph queries on every LLM prompt + MCP shell delegation for Claude Code / Cowork agents.
-
Updated
Apr 27, 2026 - Python
Local co-processor for AI coding assistants (Claude Code, Aider, Codex). Offload file ops & code tasks to Ollama. Save 60%+ tokens.
-
Updated
Jun 10, 2026 - Python
Plain-language and product-map skills for non-technical AI builders.
cursor codex ai-agents plain-language github-copilot non-technical agent-skills vibe-coding claude-code token-saving product-map
-
Updated
Jun 29, 2026 - Python
WIN10/11 & WSL2 Local File Search Skill | Millisecond Response | Token Saving for AI Agents
-
Updated
Jun 25, 2026 - Python
Transparent ztk (shell output compressor) integration for Hermes Agent. Auto-wraps non-interactive commands, saves 60-99% context tokens.
devops tooling mcp zig ai-agent claude-code context-engineering token-saving hermes-agent shell-compression
-
Updated
Jun 26, 2026 - Python
Improve this page
Add a description, image, and links to the token-saving topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the token-saving topic, visit your repo's landing page and select "manage topics."