Browse the index

The neutral meter for AI agent work: neither side keeps the count.

hand-reviewed1 starschecked today

Generate PDFs from templates via AI chat. Works with Claude, ChatGPT, Cursor, and any MCP client.

hand-reviewed1 starschecked 37 days ago

Confidence-scored domain availability checking for AI agents via CanYouGrab.it

hand-reviewed1 starschecked 13 days ago

Local-first LLM orchestration: memory, knowledge, state, routing, swarm, API discovery, plugins.

hand-reviewed1 starschecked 28 days ago

Drive a real iPhone or an iOS Simulator with an AI agent, through XCUIAutomation.

hand-reviewed1 starschecked 2 days ago

Connect any AI coding app to enterprise data sources. One binary, one JSON config.

hand-reviewed1 starschecked 3 days ago

Entropy0 MCP server — source trust and URL safety tools for AI agents

hand-reviewed1 starschecked 25 days ago

Verify whether a local Agent or MCP runtime matches an approved artifact.

hand-reviewed1 starschecked 11 days ago

Autonomous research engine: auto research from a prompt to a fully-cited academic paper via MCP

hand-reviewed1 starschecked 13 days ago

Exact arithmetic for AI agents. Two independent engines cross-check every result.

hand-reviewed1 starschecked 9 days ago

Real-time Fronius inverter data in Claude — PV, battery, grid and smart meter via local Solar API.

hand-reviewed1 starschecked 13 days ago

Regression-test AI models on real Snapdragon and Jetson hardware, with signed evidence for CI.

hand-reviewed1 starschecked 4 days ago

Tamper-evident record of what your AI agent did, plus local-first verifiable memory.

hand-reviewed1 starschecked 12 days ago

Persistent memory graph for coding agents: hypotheses, evidence, and decisions survive sessions.

hand-reviewed1 starschecked 34 days ago

Generates tests from acceptance criteria, then converges code with an agent that never sees them.

hand-reviewed1 starschecked 28 days ago

Find best-fit tools for any problem, vetted for prompt-injection risk before your agent trusts them

hand-reviewed1 starschecked 14 days ago

Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring

hand-reviewed1 starschecked 26 days ago

Precision-first security scanning for Model Context Protocol servers.

hand-reviewed1 starschecked 28 days ago

271 agent-payable tools: competitive intel, finance, KYC, compliance, ESG. x402 per-call.

hand-reviewed1 starschecked 13 days ago

Click an element in your running app or iOS Simulator, say what should change; your agent gets it.

hand-reviewed1 starschecked 9 days ago