org.opencovenant/guardai

Covenant Guard

Verified · 42 days ago

Hard spend cap, OS sandbox, and signed receipts for unattended coding agents like Claude Code.

Our take

A safety-oriented MCP server for unattended coding agents, combining spend limits, OS sandboxing, and signed receipts. It is for teams running autonomous or semi-autonomous agents where cost control and execution isolation matter as much as task output. The feature set is relevant and technically serious, but the project appears early-stage, so it deserves closer validation before being trusted in high-stakes production loops.

reviewed by hand · 2026-07-16

Something wrong or dead here? Report it

Verification record

last verified
42 days ago
github stars
8
last commit
42 days ago
archived
no
license
Apache-2.0
in registry since
2026-07-13

github.com/open-covenant/covenant

reaai

REA

Verified · 33 days ago

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

hand-reviewed291k stars232k dl/wkchecked 33 days ago

rufloai

Ruflo

Verified · 8 days ago

Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.

hand-reviewed81k stars72k dl/wkchecked 8 days ago

claude-flowai

claude-flow

Verified · 2 mo ago

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

hand-reviewed73k stars19k dl/wkchecked 2 mo ago

tldrawai

tldraw

Verified · 2 mo ago

Draw and visually collaborate with your agents on tldraw's canvas.

hand-reviewed50k starschecked 2 mo ago

codebase-memory-mcpai

Codebase Memory

Verified · 2 mo ago

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

hand-reviewed45k stars12k dl/wkchecked 2 mo ago

openseoai

OpenSEO

Verified · 4 days ago

Keyword research, site audits, rank tracking and AI visibility for your AI agent.

hand-reviewed28k starschecked 4 days ago