Agent-Native Chat alternatives

1

MCP

by decionis.com

A

Authorize consequential AI agent actions before execution

2

Local Rag

by shinpr

A

Easy-to-setup local RAG server with minimal configuration

3

Ts Core

by cyanheads

A

Agent-native TypeScript framework for MCP servers.

4

haiku.rag

by ggozad

A

Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval

5

HOL Guard

by hashgraph-online

A

Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.

6

Munim Computer Use

by munimtechnologies

A

Accessibility-first desktop control for any agent: background input, agent pointer, zoom, Chrome.

7

Formio

by form.io

C

Create and manage Form.io forms, resources, actions, roles, and projects from your AI agent.

8

Agent Memory Os

by yamantaka520

A

Local-first memory engine for AI-agent teams: team/project ACL, recall, and federated sync.

9

TaskTime Pro

by tasktime.pro

A

First-party local TaskTime Pro tools for tasks, timers, expenses, invoices, reports, and planning.

10

Husk

by husk-security

A

Local-first defensive scanner for vulnerable dependencies, leaked secrets, and risky agent configs

11

Ceraph

by ceraph.dev

B

MCP server for agent-driven React Native and Expo development and mobile testing

12

Mitos

by dovahkiin-v

A

Architectural decision memory for LLM-native workflows — markdown for humans, a graph for agents.

13

ChimeraForge

by Sahil170595

A

Local-first LLM deployment planner: GPU/VRAM sizing, cost and latency, with provenance

14

Wazap

by razvangirgiz

A

WhatsApp for your agent: chats, messages, media, contacts and groups behind MCP tools.

15

apimodels

by stimQQ

B

Image, video, chat and speech models with one API key. The model can review its own images.

16

AI Wave

by aiwave.elopstudio.com

A

AI model releases, price changes and deprecations in one feed: chat, embedding, speech, video.

17

Ratchet

by ratchetgate.com

B

Your agent asks before it acts, so the same real-world action is attempted at most once.