#anthropic

Local-first LLM token counter: exact OpenAI BPE, Claude/Gemini estimates, context-window usage. Zero network. CLI + Go library.

Local-first cost & token tracking for Claude Code, Cursor, Codex & 23 more AI coding agents — proxy-accurate per-model spend, an MCP server your agent can query, and an opt-in team rollup. 100% local, no telemetry.

该仓库未发布描述。

Claude Code with Hebrew, Arabic and Persian rendered correctly. Most terminals have no bidirectional text engine, so right-to-left output comes out scrambled. This runs Anthropic's AI agent in a terminal that gets it right, with a folder picker instead of commands. Windows and Linux, free and open source.

api-key-manager

MCP / CLI for Claude Design

A Go SDK for the Claude Code CLI: one-shot runs, interactive sessions, in-process Go tools, permission & hook callbacks, inline subagents. Behaviorally verified against the real binary.

Build, test, and deploy intelligent AI agents the Laravel way

Your tasks with 99% accuracy using any LLM (Claude, DeepSeek, Codex, Gemini, Hermes, OpenClaw, Cursor).

A status line for Claude Code: rate-limit windows, context, tokens, cache hit rate and session cost — in two lines under your prompt.

CLI to analyze Claude Code token usage, costs, and session time

GCF Go implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.

Switch Claude Code between LLM providers — no proxy, no config editing

rhachet brain.atom and brain.repl adapter for anthropic

AI 能力底座 — 统一 LLM Provider 接口（OpenAI/Anthropic/DeepSeek/Gemini/Ollama），图片生成，视频生成，Embedding，向量存储，记忆管理。Hexagon 生态 L1。

Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity receipts.

该仓库未发布描述。

Transparent logging proxy for Claude Code — audit what eats your context, with local ClickHouse/Loki/Grafana analytics

Independent Claude Skills for the whole smart home: Home Assistant, ESPHome, Node-RED, custom integrations, dashboards, and fab-ready hardware design.

🔁 Finishes your entire backlog while you sleep. The AI orchestrator that DOES the work end-to-end on ANY LLM — discover → implement → verify → merge → 24/7 — behind safety gates, at up to 90% fewer tokens. 48 extension points. Not a chatbot. A worker.

Capture and inspect Claude Code ↔ Anthropic HTTP traffic via mitmproxy, with a built-in viewer UI

Multi-account proxy for Claude Code with adaptive, rate-aware load balancing

Verifiable coding-agent harness in Go: external test gates, typed outcomes, sandboxed execution, multi-model providers, and signed proof bundles.

Personal AI powered by Claude Code, Codex and Grok Build. Remembers people, browses the web, learns over time. First party, no API keys.

Local cockpit for Claude Code CLI sessions — schedule routines, monitor token budget, manage long-running plans

SigRank MCP — the yield cascade + live leaderboard as MCP tools any agent can call. On-device token scanner + tabbed TUI dashboard. npm i -g sigrank

用最少的代码复刻 OpenClaw 的 agent 运行原理

Unofficial tool for Claude Code sessions on disk: make a session visible under your other Claude account on the same machine, or move one between project folders. Command line or GUI. Journaled, reversible, fails closed.

Validate API keys for OpenAI, Anthropic, Google Gemini, Groq, Mistral, OpenRouter, Cohere, DeepSeek, Together, Fireworks, xAI, and Perplexity. Zero dependencies. CLI + library.

Audit your Claude Code token and cost spend and monitor what your agents are doing.