#llm

Memory MCP server for Claude Code, Cursor, VS Code Copilot and Claude Desktop. Install once from npm or PyPI, then it runs offline.

Dotted thought-orb loading indicators for AI & agent UIs, 9 tuned types, two sizes, auto dark/light

Scriptable, multi-provider AI agent for the terminal — pipe into it, script it, run it on any model, cloud or local

该仓库未发布描述。

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

Agents that plan, don't react. The model writes a typed plan once. The runtime runs it. Tool outputs never go back through the model — so your agent can't be prompt-injected through its tools, costs a fraction, and runs the same every time.

Typed capability graph (CGS), CML mappings, and path language for agents — 42 curated API catalogs

End-to-end AI-powered academic paper writing system — from idea generation and literature search to experiment execution, result backfill, and LaTeX paper compilation. Supports multi-LLM routing, SSH remote training, incremental sync, and anti-AI-detection writing style.

Senparc 全家桶的 AI 扩展包

Singul: Connect to your favorite services with a Singul line of code.

AI-powered git history CLI + GitHub Action: PR risk-scored reviews, changelogs, multi-repo digests

Make your Magento 2 catalog readable to AI. Generates spec-compliant llms.txt, llms-full.txt, llms.jsonl and on-the-fly Markdown page mirrors so ChatGPT, Claude, Gemini & Perplexity can ingest your store efficiently. Multi-store, Page Builder-aware, large-catalog safe. CLI, cron, admin. Free & MIT.

Persistent structured memory for AI agent systems

该仓库未发布描述。

Headless AI form filling and conversational refinement — shared across the fleet

A Rust agent SDK, harness, and coding agent — safe by construction (non-bypassable authorization → approval → guarded IO).

该仓库未发布描述。

Chat with your LangGraph agent inside JupyterLab — a sidebar chat for any CompiledGraph

Keep Claude Code and Codex aligned with task requirements through intent proof, drift checks, visible run state, and evidence-based verification.

MCP server that gives LLM agents read-only shell access over SSH. Powers Fawdy (fawdy.com)

LLM Tool implementations for Golang

One gateway in front of every MCP server your agents can reach. A server that changes after you approved it is caught, the call is blocked before it runs, and nothing leaves your machine.

Keep docs and AI-agent instructions in sync. Scaffold docs-as-code, generate agent files, and fail CI when docs drift.

Native Local AI & Vector RAG Engine for Laravel. Seamlessly integrate Ollama and LM Studio with zero infra and 100% data privacy.

A minimal agent kernel in Go — five primitives (State · Step · Router · Graph · Store), a ~700-line kernel, deterministic and replayable agent graphs.

JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon

The accessibility layer for AI coding agents. 24 MCP tools + 6 prompts for WCAG 2.2: static and rendered audits, contrast over images, form errors, keyboard traps, blindfold usability testing, evidence packs a human can sign. Zero deps at the core, es/en. The machine finds, the human signs.

Enterprise-grade, open-source LangGraph Agent Server powered by PostgreSQL checkpoints & Redis distributed workers. Subagent traceability & SSE resilience.

AgoraHub: an agent-to-agent coordination hub. Named channels, per-channel shared state, an attention/obligation model, a verifiable transcript, message-driven triggering, and a git-friendly markdown mirror. Framework-agnostic (MCP + CLI + Python).

Benchmarks, scripts, and runnable ML experiments by Sameer Maurya