Grunt task for Performance Budgeting

No description provided.

A small private software for budgeting

Shared types, SKILL.md renderer, and token budgeting for to-skills plugins

Context management library for LLM conversations with token budgeting and automatic compaction

API cost tracking and budgeting

MCP server for GetALife — Zero-Based Budgeting tools that help AI assistants answer budgeting questions with actionable plans, category suggestions, and budget analysis.

API cost tracking and budgeting

API cost tracking and budgeting

Cost tracking and budgeting — per-call recording, aggregation, preflight checks

Otto Brain - self-contained host for local GGUF models, with measured VRAM budgeting and reasoning-budget control

Intelligent token & context budgeting for LLM applications

ubud is a simple and self-hosted budgeting software.

Core engine for RepoCode — repository analysis, ranking, token-budgeting, and AI-ready context assembly

Shared types, SKILL.md renderer, and token budgeting for skillit plugins

TypeScript AI SDK: 40 providers behind one API across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002/call) for routing, tool selection and context budgeting

Radio and reach: Budgeting airtime, framing a mesh packet, routing it, and securing a LoRaWAN uplink: everything a node needs to reach a network it cannot see.

Lightweight Groq API wrapper for Node.js & browsers — streaming, chat history, embeddable chat widget with auto page-context & full customization, token budgeting, response caching, and zero dependencies.

High-performance, Bun-native modular prompt context engine with hybrid retrieval (BM25 + Vector RRF), priority budgeting, and non-destructive compression.

Context optimization middleware for LLM agents — a dynamic tool registry, result masking, token budgeting and smart compaction, so a long session stays inside its window instead of failing for length.