#llm

Extension for the pi coding agent that intelligently routes each turn to the right LLM tier (high/medium/low) based on task intent, session budget, context size, and custom rules.

An open, versioned, verifiable standard for building AI agents — machine-readable manifests, guardrails, MCP allowlists and a CI release gate, shared across every AI coding assistant.

Open, generic LLM-driven Extractor for herrscher: distills journal+transcript into memory candidates (facts + skills).

No repository description published.

Kotlin-first framework for building Model Agnostic AI applications, RAG systems, and agentic workflows on Android and Kotlin Multiplatform.

AI-powered persistent memory system

Query-aware context trimming for LLM requests. Your context could use a trim.

SNS MyAgent — Lightweight personal AI agent CLI.

No repository description published.

Python MCP server for Blockchain Academics — crypto news, entities, academy explainers, and market data for LangChain and Python AI agents

Go-native, zero-dependency LLM command-output compressor — an embeddable take on rtk (the Rust 'token killer') with lossless-by-default compression and credential redaction.

An MCP server that gives LLMs a real interactive PTY with observability and seamless human takeover.

No repository description published.

A batch AI SDK to have one way to run batch API requests across different models

MCP server for Toss Securities (토스증권) Open API: Korean stock (KRX) quotes, holdings, orders & technical analysis for Claude and other AI agents. Read-only by default.

Supercharged vibe coding — local proxy that auto-routes Claude Code requests to any provider with transparent API translation, smart routing, and failover. Single Go binary with super ease to use TUI config wizard and live usage monitor.

Multi-provider LLM router for Go — retries, fallbacks, and streaming across OpenAI, Anthropic, Gemini, and more

See where it leaks, stop paying for it — a live Claude Code status line that prices every turn, your subagents, cache rebuilds, plus limits, context and git.

Slim SDK for Soothe plugins and shared contracts (events, wire, display, protocols)

A high-performance, embedded Go telemetry engine designed to aggregate, parse, and visualize API costs and token utilization across autonomous AI agents.

Composer plugin that automatically discovers AI Mate extensions on install/update

Security scanner and introspection tool for MCP servers. Connect, inspect, detect injection patterns, find tool shadowing, baseline for drift. Single binary, zero dependencies, Go stdlib only.

Client-side HTTPS egress proxy for TokenSaver — MITM capture for Claude Code / Cursor / agents.

run your agent. it can't destroy your machine.

CLI that audits MCP (Model Context Protocol) server implementations for spec conformance and quality — missing descriptions, undocumented params, unhandled errors, README coverage.

Dynamic documentation fetching CLI that converts entire documentation sites to single markdown files for AI/LLM consumption

Production-ready TypeScript Agent SDK for building intelligent AI agents with memory, tools, guardrails, handoffs, and tracing.

No repository description published.

Your agent forgets; nem doesn't. mnemonics encodes a session's decisions, edge-cases and facts into immutable, recallable structure — versioning agent context the way git versions code, shared across Claude & Codex.

Robust extraction of structured payloads from LLM output via sentinel blocks (<<<TAG>>> … <<<END>>>). Survives quotes, newlines & braces that break JSON.parse. 10 language ports, one spec.