#llm

Use LLMs and LLM Vision (OCR) to handle paperless-ngx - Document Digitalization powered by AI

MCP Server for InfluxDB 3

A Vercel AI SDK provider for Ollama built on the official ollama package. Type safe, future proof, with cross provider compatibility and native Ollama features.

Faster Agentic Coding with confidence in every commit

An independent .NET implementation of a Neo4j-backed memory provider for AI agents. Persistent graph-native memory for Microsoft Agent Framework, with GraphRAG interoperability for Neo4j.

Juggernaut is a one-command setup tool that configures Claude Code to use AWS Bedrock, with cross-platform support (bash/zsh/fish/PowerShell), dry-run mode, and validation scripts.

No repository description published.

The memory layer for AI-native development - giving AI persistent understanding of your software projects.

Repair broken JSON in Rust — fix quotes, commas, comments, truncation, and 30+ issues from LLM outputs

CodeWiki-Plus is a repository knowledge engine driven entirely by the AI IDE's own model via MCP (Model Context Protocol): zero LLM configuration for Wiki generation, plus a full knowledge management engine on top — retrieval, notes, task memory, and team telemetry.

Lighthouse for MCP — score any MCP server 0–100.

Markdown-first, long-term memory infrastructure for AI agents. Hybrid BM25 + semantic search across markdown/code files via MCP.

FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.

Local, BYOK code review for any language. No SaaS, no telemetry.

Smart git diff context for LLMs and AI agents: budgeted fragment selection, deterministic, MCP server included

Persistent memory for AI coding agents

Open-source, single-binary, self-hosted AI agent — your models and data stay on your machine. A coding agent on par with Claude Code and a personal assistant lighter than OpenClaw, across eight interfaces (TUI, CLI, Web, desktop, IM, VS Code, Obsidian, Mobile), all in one MIT-licensed Go binary running on any model.

A Model Context Protocol (MCP) server that enables AI agents and LLMs to query and analyze Prometheus metrics through standardized interfaces.

Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.

Open-source, OpenAI-compatible AI gateway with health-aware routing, failover, and live telemetry (cost, latency, errors). Built for production.

powerful and modern telegram bot api sdk for node.js and typescript 😁

Synthetic data that hits the numbers you declare, exactly. Multi-table with verified foreign-key integrity, deterministic, no model in the data path. Python + MCP server. In simple terms, a powerful demo data generator for sales/demos/seed data.

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

Stop your coding agent reading the wrong files. Compiler-grade TS/JS repo map — 100% precision on blast radius vs grep's 60%, measured on public repos. CLI + MCP server, fully local, no vector DB.

MCP budget and risk authority for Cycles — runtime governance for Claude, Cursor, and Windsurf

Cycles budget and action guard for OpenClaw agents

Turn research PDFs into grounded Markdown drafts — driven by any token-free AI coding-agent session (Claude, Codex, Gemini, Copilot, Cursor, Amp, Crush, Goose, Grok) when online, local Ollama when offline.

AI data-isolation verification — prove no user or customer can reach another's data across 13 AI surfaces, with tamper-evident evidence anyone can verify.

Run AI coding agents (Claude, Codex, Gemini …) unattended — auto-answer prompts, auto-retry on rate limits, and list/tail/steer every agent locally or from agent-yes.com

Any PyTorch model to NNEF exchange format