Category

executor

Local integration layer that lets AI agents discover and securely call OpenAPI, MCP, GraphQL, or custom JavaScript functions. Centralizes a shared tool catalog, auth, and policy surface across multiple agents, with a local web UI and CLI for runtime control.

oMLX

Local LLM inference server for Apple Silicon that exposes an OpenAI-compatible API and a macOS menubar app. Uses continuous batching and a two-tier KV cache (RAM + SSD in safetensors) to persist context across restarts, enabling practical multi-model serving and fast local coding workflows.

OmniRoute

Acts as an OpenAI‑compatible local and cloud gateway that routes requests across 100+ LLM providers with smart routing, load balancing, retries and fallbacks. Adds policies, rate limits, semantic caching and observability for reliable, cost‑aware inference in Docker, Electron or npm installs.

Context Mode

Dramatically reduces AI agents' context usage by sandboxing large tool outputs and indexing only relevant snippets into a searchable SQLite FTS5 (BM25) knowledge base, improving session continuity and privacy. Deploys cross-platform hooks and sandbox tools to cut context size by ~98% and avoid dumping raw logs into the model's window. ([github.com](https://github.com/mksglu/context-mode/blob/main/README.md?utm_source=openai))

Claude for Financial Services

Provides named agents, reusable skills, and MCP data connectors for common financial‑services workflows (investment banking, equity research, private equity, wealth). Available as Claude Cowork plugins or deployable Claude Managed Agents templates—designed as enterprise-ready templates, not turnkey investment advice.

codebase-memory-mcp

Indexes codebases into a persistent, queryable knowledge graph for AI coding agents, enabling full-repo indexing in minutes and sub-millisecond structural queries. Bundles 158 vendored tree-sitter grammars, a Hybrid LSP resolver, built-in embeddings, and 14 MCP tools for search, trace, and architecture analysis.

Rapid-MLX

Runs local AI models on Apple Silicon as an OpenAI‑compatible server, emphasizing low latency, prompt caching, and reliable tool-calling. Optimized for M1–M4 Macs with multimodal support and drop‑in compatibility for IDEs and agent frameworks.

agentmemory

Provides persistent, searchable memory for coding agents (Claude Code, Cursor, Gemini CLI, etc.), automatically capturing tool usage and session facts. Combines BM25, vector embeddings and a knowledge graph for hybrid retrieval, reducing token costs and re-explaining between sessions.

code-review-graph

Builds a local structural knowledge graph of a codebase so AI coding assistants read only the minimal, relevant code during reviews and daily tasks—reducing tokens used while providing blast-radius impact analysis, incremental updates, and MCP integrations.

OpenSEO

Provides an MCP server and agent skills so AI agents can run keyword research, inspect SERPs, compare domains, and manage backlinks using your DataForSEO data. Self‑hostable TypeScript project with an optional hosted UI (openseo.so) and pay‑as‑you‑go data usage.

WeChat 4.x Database Decryptor

Extracts derived keys from running WeChat 4.x processes to decrypt SQLCipher 4 databases and .dat media files, and provides a real-time message monitor with a Web UI. Cross-platform (Windows/Linux/macOS) but requires process-memory or local-data access and is intended for decrypting your own WeChat data only.

Claude Code Agent Monitor

Real-time monitoring and control dashboard for Claude Code agents — tracks sessions, agent/subagent activity, tool calls, and live analytics. Local-first integration via Claude Code hooks, with Kanban/status board, MCP tool catalog, and web/desktop clients.