#llm

Give your AI assistant secure, read-only access to your bank accounts. MCP server supporting Plaid, Teller, Enable Banking, and Tink.

Predict rate-limit cutoffs inside your AI agent. Local MCP server + CLI that tracks Claude Max, ChatGPT Plus/Pro/Team, GitHub Copilot, Cursor plan windows and warns before you hit the cap.

JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).

A coding agent CLI that runs like an engineering org — role routing, plan DAGs, approvals, memory, and a 10-platform chat gateway. Apache-2.0.

Create multi-agent workflows with AI and Language Models using OTP components in Elixir for reliable and scalable automation.

Validate and retry LLM outputs for ruby_llm. Describe the JSON response you expect, fall back to a stronger model when the cheaper one fails the rules, and gate CI on regressions — all as one contract object per step.

Security boundary CLI proxy between AI coding agents and your shell — redacts secrets, neutralizes prompt injection, wraps untrusted terminal output, and audits every command. Single Rust binary.

Static LLM model metadata registry for Go apps: model IDs, aliases, providers, capabilities, tags, context windows, and localized descriptions.

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

3ds Max adapter for the DCC Model Context Protocol ecosystem

Provider-agnostic TypeScript agent SDK — pluggable providers, built-in tools, skills, memory, and MCP

AI for the Command Line

Provider-agnostic, modality-aware language model router with fallback for the Vercel AI SDK.

Stop degrading your model's reasoning. A minimal, zero-config AI coding agent. Enforced ephemeral subagents keep context pure. From tiny local models up to Sol, Fable and Kimi K3.

Run any local LLM engine, auto-tuned to your GPU — polished web UI + OpenAI/Anthropic-compatible API. Point Claude Code at your own machine in one command. No Electron, no Python, offline-first.

Simple router to aggregate multiple LLM providers with optional smart routing and MCP aggretation.

Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · Hermes · VS Code · Windsurf.

In today's rapidly evolving landscape, vale-ai-tells is a comprehensive, cutting-edge Vale style package that empowers writers to seamlessly delve into the rich tapestry of AI tells. It's not just a rule set; it's a game-changer that supercharges your prose, unlocks new possibilities, and really lands. Ship cleaner prose. Full stop. 🚀

AI-native rate limiting SDK for Go, Node.js, and Python — middleware, not a proxy

Verboo is a Fork of Openclaude and Is Open-source coding-agent CLI for Verboo Code

Hand a coding-agent session to another agent. Reads local Claude Code, Codex, Antigravity, OpenCode & Pi Agent history; forks natively or seeds a clean transcript.

Identity, memory & collaboration platform for AI agents — facts, memories, secrets, and inter-agent messaging via a CLI, MCP, and a Go server.

A Ruby Implementation of the Model Context Protocol

No repository description published.

Open-source Go agent runtime for autonomous AI systems and multi-agent automation. MCP, RAG, 15+ LLM providers and 60+ built-in tools in a single binary.

MCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs across sessions with 68.5% fewer tokens than re-reading context. No LLM, no server; works with 15+ agents.

A terminal-native AI coding agent — a fast, scriptable TUI CLI for builders.

Offline-first hybrid MCP knowledge base for a Salesforce org.

Local memory + orchestration layer for custom LLM agents: SCOPE-style tactical/strategic memory over execution traces, Qdrant-backed, polyglot subprocess tools, agent-as-tool composition.

Python framework for efficient and precise interpretability research on multi-agent conversations.