[ACL 2026 Oral] "LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"
-
Updated
May 22, 2026 - Python
#
token-efficiency
Here are 114 public repositories matching this topic...
The Context OS for Autonomous AI Agents. Distill terminal noise into pure semantic signal, stop agent hallucinations, and cut token costs by 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 token-savings
-
Updated
Jun 15, 2026 - Rust
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
Jun 16, 2026 - TypeScript
An agentic memory database that cuts session tokens by 82–99%. One portable SQLite file — your agent's memory, anywhere.
cli golang sqlite mcp opencode ast developer-tools knowledge-base codex ai-agents fts5 gemini-cli model-context-protocol mcp-server agent-memory claude-code llm-tool token-efficiency openclaw
-
Updated
Jun 15, 2026 - Go
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 27, 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 15, 2026 - Python
Claude Code skills for developers who code like cats — never more effort than the problem requires.
cat skill lazy claude cost-saving llm anthropic ai-productivity claude-code token-optimization token-efficiency claude-skills think-twice
-
Updated
Jun 11, 2026 - JavaScript
One-Click Private AI Stack on your VPS. Deployed with a pre-built 50k-line Next.js Aircraft Carrier & Zero-Agent Design System. Shifting layout assembly to atomic MCP commands to eliminate file reads and drive AI token spend to absolute zero.
terminal self-hosted multi-agent free developer-tools hermes ai-agents coding-assistant cloud-free ai-workspace llm-ui parallel-routing gemini-cli lightrag claude-code token-efficiency codex-cli
-
Updated
Jun 16, 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
Jun 14, 2026 - TypeScript
The AI-native wire format for structured data. 100% comprehension on every frontier model. 71% fewer tokens than JSON. 33B+ lossless round-trips across 5 formats. Spec v3.1 Stable.
mcp gemini tokens openai data-serialization structured-data gcf json-alternative ai-agents wire-format agent-communication llm anthropic model-context-protocol mcp-tools token-optimization token-efficiency llm-benchmark toon-alternative graph-compact-format
-
Updated
Jun 16, 2026
A curated list of strategies, tools, papers, and resources for reducing LLM token costs and improving efficiency in production.
machine-learning awesome ai openai awesome-list claude cost-optimization inference-optimization kv-cache large-language-models llm prompt-engineering generative-ai prompt-caching context-window prompt-compression llm-cost token-optimization token-efficiency model-routing
-
Updated
Jun 14, 2026
Open-source platform for token-efficient AI agents. Self-host with docker compose up.
-
Updated
Jun 3, 2026 - Python
Coherent Workspace — the data plane for shared agent state
python multi-agent-systems state-synchronization autogen cache-coherence ai-agent langchain llm-agent crewai agent-memory token-efficiency
-
Updated
Jun 16, 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
Jun 8, 2026 - TypeScript
A Codex skill for token-efficient subagent delegation and lean handoffs.
-
Updated
Mar 21, 2026
MCP proxy: zero-code GCF adoption. Wraps any MCP server, converts JSON to GCF mid-flight. 53-71% fewer tokens. Works with any structured data.
streaming proxy mcp json-rpc stdio data-serialization structured-data gcf json-alternative ai-agents wire-format llm model-context-protocol mcp-server mcp-tools token-optimization token-efficiency mcp-proxy context-engineering graph-compact-format
-
Updated
Jun 14, 2026 - Go
Coding agents forget your repo. mcp-brain is the missing memory layer — repo-aware, team-aware, lifecycle-aware. 63% Hit@10, zero LLM cost. Works with any MCP client.
ai mcp developer-tools persistent-memory code-generation claude ai-engineering llm prompt-engineering llm-tools ai-productivity llm-memory context-management context-compression token-optimization token-efficiency token-budget context-overhead team-awareness
-
Updated
Apr 27, 2026 - Python
A lightweight Python protocol and tool for agent-oriented documentation
skills protocol opencode docstring codex claude ai-agent llm prompt-engineering hallucination-mitigation vibe-coding claude-code token-efficiency coding-agent context-engineering claude-skills agent-readable agent-help
-
Updated
Jun 12, 2026 - Python
GCF Go implementation. 100% comprehension. 71% fewer tokens than JSON, 25% fewer than TOON. 200M round-trips verified. v1.2.0.
go golang encoder mcp decoder gemini openai data-serialization structured-data gcf json-alternative ai-agents wire-format llm anthropic model-context-protocol mcp-tools token-optimization token-efficiency graph-compact-format
-
Updated
Jun 15, 2026 - Go
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."