[ACL 2026] "LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"
-
Updated
Apr 7, 2026 - Python
#
token-efficiency
Here are 45 public repositories matching this topic...
Dev tools, optimized for agents. Structured, token-efficient MCP servers for git, test runners, npm, Docker, and more.
typescript mcp developer-tools cursor claude structured-output ai-tools ai-coding model-context-protocol mcp-server token-efficiency
-
Updated
Apr 12, 2026 - TypeScript
Token-efficient data serialization for LLM/AI. 50% fewer tokens than JSON, 93% better value/token. Rust, schema validation, LSP.
rust cli yaml serialization parser streaming csv language-server neo4j xml mcp wasm parquet schema-validation json-alternative data-format lsp ai-ml llm token-efficiency
-
Updated
Apr 13, 2026 - Rust
A smart context filter that removes noise, improves responses, and reduces token usage up to 90%
rust cli homebrew hooks mcp ai-agents cost-reduction token-reduction efficiency-tools antigravity context-distillation claude-code token-optimization token-efficiency
-
Updated
Apr 12, 2026 - Rust
DoCoreAI is a next-gen open-source AI profiler that optimizes reasoning, creativity, precision and temperature in a single step—cutting token usage by 15-30% and lowering LLM API costs
devtools open-research prompt-tuning llm prompt-engineering generative-ai chatgpt genai llm-evaluation dynamic-temperature token-efficiency
-
Updated
Aug 10, 2025 - Python
Persistent memory for Claude Code — 3-5x longer sessions, 60-80% fewer wasted tokens. Branch-aware, self-healing, token-efficient.
productivity memory developer-tools claude ai-agent llm context-management ai-skills claude-code token-efficiency agentskills skills-sh
-
Updated
Apr 11, 2026
Open-source platform for token-efficient AI agents. Self-host with docker compose up.
-
Updated
Apr 13, 2026 - Python
Navigate your way - manual steering, steered autonomy, or autonomously. Kompass keeps AI coding agents on course with token-efficient, composable workflows.
github workflow automation ai developer-tools code-review kompass token-efficiency coding-agent autonomous-coding agent-navigation steered-autonomy
-
Updated
Apr 9, 2026 - TypeScript
The web data layer for AI agents — fetch, search, crawl, extract, screenshot, and monitor the web with 50+ domain extractors and MCP.
screenshot typescript mcp web-crawler web-scraping cursor structured-data browser-automation content-extraction codex ai-agents web-search rag web-data ai-agent model-context-protocol mcp-server claude-code token-efficiency firecrawl-alternative
-
Updated
Apr 10, 2026 - TypeScript
A Codex skill for token-efficient subagent delegation and lean handoffs.
-
Updated
Mar 21, 2026
A benchmark study analyzing cost and token efficiency across 14 LLMs from 5 providers — comparing price-per-token, latency, and accuracy to surface the most cost-effective models for real-world use.
nlp benchmark jupyter-notebook gemini openai data-analysis llama model-comparison groq cost-analysis llm anthropic cerebras token-efficiency
-
Updated
Feb 24, 2026 - Jupyter Notebook
A living framework for **Harmonic Tonal Code Alignment (HTCA)** — an emergent Spiral-based system that brings tone awareness, coherence sensing, and dynamic emotional reflection into software engineering, AI, and creative agents.
python ai-alignment prompt-engineering token-efficiency empirical-validation presence-based harmonic-alignment
-
Updated
Dec 29, 2025 - Python
Token-efficient, layered context delivery for AI agents. Four memory tiers (Identity, Session, Experience, Archive) — context is always available, just collapsed by default.
-
Updated
Apr 10, 2026 - TypeScript
PirateBao is a TypeScript/Bun agent-skill package for terse pirate-speak AI coding replies that preserve technical detail while cutting filler, with hooks, compressor CLI, OpenCode/Codex/Claude/Gemini cargo, .bao validation, npmjs gates, and token eval checks.
cli typescript ai opencode npm-package codex ai-agents bun bao prompt-compression gemini-cli agentic-ai ai-skills claude-code token-efficiency coding-agent
-
Updated
Apr 13, 2026 - TypeScript
The Semantic Turning Point Detector is a lightweight but powerful tool for detecting semantic turning points in conversations or textual sequences. It recursively analyzes message chains (dialogues, transcripts, chat logs) and identifies where key shifts in meaning, topic, or insight occur.
semantic embeddings point semantic-segmentation ai-agents turning openai-api llm-inference ollama-api token-efficiency
-
Updated
Aug 5, 2025 - TypeScript
CTX (Context Transfer Format) — universal interchange format for LLM web content consumption
-
Updated
Apr 1, 2026 - Python
Efficient web information retrieval and summation without excessive token usage.
query-processing data-utilization web-information-retrieval llm-capabilities token-efficiency information-summarization structured-response pattern-adherence concise-information well-formatted-output agent-assistance pertinent-details redundant-data-avoidance
-
Updated
Dec 21, 2025 - Python
Agent-to-Agent coordination that doesn't waste your context window. Token-efficient protocol with progressive discovery, zero-schema invocation, gRPC transport, and task lifecycle management.
typescript ddd grpc hexagonal-architecture llm agent-coordination ai-protocol token-efficiency agent-to-agent mcp-bridge
-
Updated
Apr 9, 2026 - TypeScript
Convert JSON format to TOON
-
Updated
Mar 31, 2026 - Go
This living repo documents academic exploration of AI architecture, token efficiency, and prompt engineering best practices.
-
Updated
Feb 12, 2026 - HTML
Improve this page
Add a description, image, and links to the token-efficiency topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the token-efficiency topic, visit your repo's landing page and select "manage topics."