Gdharness alternatives

1

Async Parallel Antigravity for Codex & Claude Code

by varadfromeast

A

Run parallel, resumable, human-operable Antigravity CLI sessions from any MCP agent harness

2

Ask Codex

by Lykhoyda

A

Bridge Claude with OpenAI Codex CLI for AI-to-AI collaboration, code review, and second opinions

3

Ask Claude

by Lykhoyda

A

Bridge Codex and other MCP clients with Anthropic Claude Code CLI for read-only second opinions

4

ContextStream MCP Server

by contextstream

A

Project memory, semantic code search, and grounded agent context.

5

Google Surf

by HarimxChoi

C

Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.

6

Agent Comms

by ExaDev

A

Cross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCP

7

Projectmem

by riponcm

A

Coding agent memory — one local MCP server for every project. Warns before repeating failed fixes.

8

Sanity

by www.sanity.io

A

Direct access to your Sanity projects (content, datasets, releases, schemas) and agent rules

9

Claudinho

by arturogarrido

A

Live 2026 World Cup scores, fixtures & standings for your AI agent. No keys. Unofficial fan project.

10

Bomly

by bomly-dev

B

Give your coding agent the dependency graph it is about to change: scan, diff, explain, audit

11

KLYPIX Project Brain

by dahshanlabs

B

Active state management for multi-agent coding: a shared, versioned project brain over MCP.

12

Kosha Model Discovery

by sriinnu

B

Tells your agent which model to use and what it costs, across 45 providers and local runtimes.

13

Formio

by form.io

C

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

14

Agent Memory Os

by yamantaka520

A

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

15

TaskTime Pro

by tasktime.pro

A

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

MCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.

17

Wundervault

by wundervault

C

Zero-knowledge MCP secrets vault for AI agents: secrets injected at runtime, never seen by the model

18

Aletheia Runtime Safety & Scope Creep Filter

by vikasny30

B

Deterministic pre-execution filter that blocks known scope-creep and prompt-injection tool calls

19

Create Starter

by starter-series

A

Scaffold Starter Series projects and check release, deployment, security, and agent instructions.