token-budget

Run-aware token governance for multi-agent systems. Cap spend and steer behavior across a whole agent workflow, not per request, with a shared ledger and in-path enforcement.

Cross-agent skill quality gate for SKILL.md files. Validates frontmatter, scores description discoverability, checks file references, enforces three-tier token budgets, and flags compatibility issues across Claude Code, VS Code/Copilot, Codex, and Cursor.

Code intelligence for agents: find the code that matters and keep your context window and tokens lean.

让 Agent 高效又守纪律 — 不止省 token：ZeroToken 压缩无效上下文/推理/输出；尉缭子十原则约束权限边界、单一指令、先谋后动、验证先于结束；附 Unicode 编码规范、搜索规范、六种任务模式。More than token savings: ZeroToken efficiency + AI coding discipline for Reasonix / Codex / OpenCode / Hermes

Open-source edge engine to control API request budgets and enforce fair usage.

Self-hosted spend firewall and gateway for LLM ( OpenAI / Anthropic / Gemini ). Hard per-user & per-project budget caps that block runaway costs before the API call, plus cost-per-customer tracking, semantic caching, and failover. One line of code, single Go binary.

Open-source platform for deterministic, token-aware context selection for AI agents and LLMs

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.

Runtime containment kernel for LLM agents. Enforces budget, step, retry, and circuit-breaker limits before the model call.

Don't go into production without these - 3 auto-triggering Claude Code skills for cost and drift prevention. 6 months of practitioner notes.

A drop-in SKILL that forces AI coding agents (Claude Code, Codex, Cursor, Cline, Roo, Windsurf, Copilot, Augment, Aider, …) to deliver exactly what was asked — minimum diff, zero unsolicited files, terse output by default.

TokenSched 给 Claude Code 的 token 预算装上了一个 CPU 调度器：它按子任务期望��预分配预算、预测超支，并在 5 小时窗口耗尽前自动把低价值工作降级到 Haiku 或抢占——把硬截断变成可调度的软退让。

Open source AI cost tracking. Know exactly what your AI costs — per feature, per user, per project.

Constant token budget for long-form LLM writing. Chapter 1000 costs the same as chapter 10 (61,331 → 4,396 tokens measured). Zero dependencies, runs on Cloudflare Workers.

Embeddable, zero-dependency durable execution for agents and NHEs. Deterministic replay, retries, cycle detection, a token budget, and a multi-agent task board, with no sidecar service.

TypeScript SDK that adds cost limits, token/call budgets, timeouts, and circuit breakers to AI agent/LLM workflows, with adapters for OpenAI, Anthropic, Vercel AI, and observability/reporting support.

Zero-dependency context-window packer for LLM chat: fit a conversation into a token budget (middle-out, drop-oldest, priority, pinning).

Core library: scoring, selection, and caching for the Context Engine

ContextOps toolkit for production AI agents. Compile, govern, scan, visualize & optimize LLM context before every model call — token budgets, policy governance, PII/secret scanning, Context Bill of Materials, diffing, Context MRI, MCP budgeting. Framework-agnostic. Local-first. Deterministic.

CLI for building, resolving, and inspecting context caches