Token-aware, multi-format text chunking library with language-aware semantic splitting
Context Intelligence Engine with CCP. 34 MCP tools, 8 read modes, 90+ compression patterns, cross-session memory (CCP), persistent AI knowledge with temporal facts + contradiction detection, multi-agent context sharing + diaries, LITM-aware positioning, AAAK compact format, adaptive compression with Thompson Sampling bandits. Supports 24 AI tools. Reduces LLM token consumption by up to 99%.
Context Runtime for AI Agents with CCP. 63 MCP tools, 10 read modes, 60+ compression patterns, cross-session memory (CCP), persistent AI knowledge with temporal facts + contradiction detection, multi-agent context sharing, LITM-aware positioning, AAAK compact format, adaptive compression with Thompson Sampling bandits. Supports 24+ AI tools. Reduces LLM token consumption by up to 99%.
ilo - the token-minimal programming language AI agents write
Blazen - A Rust-native AI workflow engine with event-driven orchestration
An unofficial Ruby wrapper for Tiktoken, a BPE tokenizer written by and used by OpenAI. It can be used to count the number of tokens in text before sending it to OpenAI APIs.
An unofficial Ruby wrapper for Tiktoken, a BPE tokenizer written by and used by OpenAI. It can be used to count the number of tokens in text before sending it to OpenAI APIs. This is a fork of tiktoken_ruby by IAPark, which has been cross-compiled for multiple platforms. This way compilation with Rust extensions doesn't need to happen wherever you are deploying it.