#llm

Real-time, AI-assisted log triage CLI/TUI in Go. Silent on noise, speaks on signal — scores logs locally and escalates only genuine anomalies to an LLM (local Ollama by default).

TOON encoding for Laravel. Encode data for AI/LLMs with ~50% fewer tokens than JSON.

Qualify repeated categorical AI-agent evidence before it becomes a regression reference

A command-line toolbox for subtitle files

A Typescript library to use LLM providers APIs in a unified way.

A CLI that makes it easy way to find, run, and manage local LLMs.

Zero dependency plug-and-play templating for Bun

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

Implementation of LangGraph framework for GoLang.

Makes AI stateful across sessions. Workflow: chat → idea → design → reqs → plan → do_step(s) → done, with fresh scoped context, staleness detection, and human approval at every phase. Roadmap & history of shipped features.

Run, watch, and meter Claude Code, Codex CLI, Gemini CLI, OpenCode, and Kiro from one CLI. Normalized events, cache-aware token usage, cost accounting verified against each agent's own records, budget caps, OpenTelemetry gen_ai spans, Langfuse traces, and a live web dashboard + MCP server.

All-in-one engineering workflow & knowledge engine for Claude Code. One-command install, runs standalone (Node >=18, no bun). L0-L3 task classification, 13 runtime invariants, code review, browser QA, security audit, and a deduplicated knowledge base that compounds across tasks.

A runtime where decision models propose and your code decides: typed questions, hard rules, quotes checked against the text, escalation with a guaranteed error budget, replayable traces. Works with any System One model.

Whole-book translation pipeline — scouts the book, translates in context, edits, adds footnotes. epub, fb2, pdf, txt, html in; epub, fb2, html, txt out.

AWS Bedrock platform bridge for Symfony AI

ChromaDB vector store bridge for Symfony AI

Doctrine DBAL message store bridge for Symfony AI Chat

PostgreSQL pgvector vector store bridge for Symfony AI

Qdrant vector store bridge for Symfony AI

记忆的编辑判断：什么值得记、归哪个桶、几张卡、什么时候该整理。不调模型、不碰存储。

Provider-neutral, self-hosted reference runtime for autonomous agents (Toll Bench harness).

The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!

Official typescript implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.

A superfast proxy and smart load-balancer for AI Inference — virtualize models, share local and provider back-ends, optimal caching, lock-in sampling parameters, debug message flow and obtain OTel metrics

🔁 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.

Utility-first helpers for the Web Streams API, aimed at streaming and transform pipelines.

The provider-agnostic AI toolkit for Python

Опис репозиторію не опубліковано.

MCP server for Wan AI video generation via AceDataCloud API

Adicione o conhecimento do seu banco de dados para seu Agente de IA