tokenomics
token-optimizer
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
- 3k
- Python
- 2 d ago
howcryptoworksbook
A free, open-source book that explains how crypto actually works. 15 chapters covering Bitcoin, Ethereum, Solana, DeFi, MEV, market structure, custody, stablecoins, governance, quantum resistance, and prediction markets.
- 900
- 6 wk ago
entroly
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.
- 488
- Python
- Apache-2.0
- 12 h ago
awesome-ai-tokenomics
A curated list on AI token economics: what tokens cost, where they get wasted, and how to cut the bill. Tools, benchmarks, papers, and copy-paste configs for the token economy of LLMs and coding agents.
- 219
- Python
- CC0-1.0
- 8 d ago
token-meter
Open-source, local-first AI coding agent usage and cost dashboard for Claude Code, Codex, Cursor, OpenCode, Kiro, and Pi.
- 155
- Python
- MIT
- 1 d ago
rightsize
Make every Claude token count. rightsize picks the right model and effort for each prompt, while keeping cache and context costs low. It learns how you work and gets better over time.
- 45
- TypeScript
- MIT
- 3 d ago
kyber-weave
Agentic coding framework and meta-harness for planning, building, reviewing, and tuning software across coding agents. Portable agent squads, skills, governed project knowledge, quality gates, and local token observability. Human judgment. Agent speed.
- 23
- C#
- MIT
- 3 d ago
virtue
Rule-based conversational NLP engine & real-time crypto financial calculator built with Next.js 16, React 19, and Binance API
- 4
- TypeScript
- MIT
- 5 wk ago
surplus
MIT CLI that uses spare weekly allowance for stronger Claude Code and Codex sessions.
- 1
- TypeScript
- MIT
- 3 wk ago
join-cheaperuh-party
Join cheaperuh (čipera) PARTY - Can AI really adjust its intelligence to real tasks? [AI Tinkerers Prague]
- 1
- TypeScript
- MIT
- 2 mo ago
why-hybridai-rsvp
Private AI on NeoClouds - Large Open Weight models need a lot of VERY large GPUs (aka massive infra)
- 0
- HTML
- MIT
- 2 mo ago
localai-isnot-cheap
EDU AI LAB: Local AI is not CHEAP at ALL! - Every AI token carries a COST! How to measure them?
- 0
- Python
- MIT
- 3 mo ago





