Tagged “openai”

headroom

by headroomlabs-ai

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

osaurus

by osaurus-ai

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

archestra

by archestra-ai

Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator

cuecards

by opencue

Agent profile manager for Claude Code & Codex. Per-directory profiles select which skills, MCP servers, and plugins load — automatically, before launch. Install: npm install -g cue-ai

diffctx

by nikolay-e

Smart git diff context for LLMs and AI agents — selects the minimal code fragments needed to understand a change, under a token budget. Deterministic, local, MCP server included. Also exports a full codebase to YAML/JSON/MD.

AgenticLedger

by ShekharBhardwaj

Local-first flight recorder for AI agents: every LLM call, tool call, cost, and loop captured by a transparent proxy. Zero code changes.

cxws-mcp

by NEURAX-FX

A standalone MCP server for Codex cloud web search

upilot

by codingriver

upilot Unity Editor automation bridge for AI agents and MCP clients

CastCLI

by JustinANelson

Java 21 LLM orchestration harness: routes tasks between local Ollama models and frontier cloud models (OpenAI/Anthropic/Gemini) with MCP client/server support, multi-agent pipelines, and durable shared memory.

zero-mcp

by nikosv

Zero-boilerplate, lightweight and fast MCP server toolkit. Skip the weight of `@modelcontextprotocol/sdk` and start shipping MCP servers in minutes with minimal code.