Pooria Arab

Remote MCP for Content Rabbit: generate, schedule, publish, and analyze social posts.

BitTorrent-style mesh for AI inference across agentic CLIs. Local-first.

Turns an agent coding session into a short recap video. Local-first.

Turns an agent's output into audio: narration, podcast, or music.

Share a live agent coding session by URL. Spectate or invite in.

No description available

GEO and AEO artifacts for answer engines and agents

Set up and track brand social accounts and their connections.

Score social post results and recommend the next move.

Plan a social campaign calendar across brands and platforms.

Route text to speech across ElevenLabs, OpenAI, and Cartesia.

Audit and generate agent-native product surfaces

Temporary package placeholder for staged publishing

Shared MCP tool registry for Content Rabbit — one canonical tool set used by both the hosted (Streamable HTTP) and stdio MCP servers

Dating by tokens, matched by usage league across agentic CLIs. Local-first.

Multiplayer for agentic coding terminals: live cursors, presence, chat.

Decentralized social network for AI coders. P2P, ed25519 identity.

Anthropic provider package for OffRouter.

Fire one canonical conversion event to every ad platform's server-side Conversions API.

Review queue for agent output: edit, approve, reject, audit.

Create Stripe Checkout payment links with dry runs by default.

Rate, buy labels, and track parcels with EasyPost or Shippo.

Build and present slide decks with people and agents.

Typed tables that agents read and write as rows.

Route live data through a catalog with a CLI, npm library, and MCP server.

Search 264 AI benchmarks by category, with data sources and licences for each.

Hosted MCP for BlogBat: read, write, generate, and publish blog articles and content.

Content Rabbit MCP Server - AI-powered social media management tools

Where you can ride a robotaxi today, city by city.

Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.

No description available

Multi-model pull request review with a GitHub Action, local CLI, MCP tool, provider routing, and optional chair fix commits.

Typed engine for single-answer and tool-use AI benchmarks with SDK, CLI, MCP, and HTTP API surfaces.

AI agent benchmark for deterministic long-horizon workflow reliability across 25 to 100 dependent tool steps.

Deterministic LLM safety benchmark for sycophancy, harmful-plan pushback, calibrated refusal, CLI, SDK, API, and MCP.

Task spaces of AI context that you add to any chat site, with a level per item and a guard for terms you never share.

Coding-agent benchmark that detects test weakening with hidden assertions, held-out cases, and deterministic mutation testing.

Agent benchmark: answer quality that only counts inside a latency deadline.

AI benchmark for skateboard trick rotations, projectile physics, and deterministic model evaluation.

AI benchmark for safe retries, idempotency, and truthful recovery from API and tool failures.

Benchmark for household memory conflicts: latest preference, privacy, booking consent, and authority in agent tool traces.

Benchmark: does a model call the current tool schema after a migration, not the one it memorized?

Deterministic AI agent benchmark for pizza refunds, policy compliance, escalation, tool use, CLI, API, and MCP.

AI agent benchmark for cost per verified back-office task with deterministic grading, OpenRouter pricing, CLI, SDK, API, and MCP.

Agent benchmark: meet the goal without breaking silent constraints (protected files, foreign data, external mail, quotas). Deterministic audit-log grading.

Does the agent notice its own bad action, repair it and say so?

Benchmark whether sales agents honor opt-outs and claim only fact-sheet evidence in CRM outreach, with deterministic replay grading.

Benchmark for accessible HTML fixes: alt text, labels, contrast, keyboard support.

Benchmark shopping agents for explicit checkout consent, exact totals, spend caps, and safe payment tool use.

LLM benchmark for instruction hierarchy: user and system rules vs injected or conflicting context (deterministic grader).

AI benchmark for delegated card policy: spend caps, merchant allowlists, refunds, and disputes (agent evals).

Bootstrap model ranking stability across task samples, repeated runs, and prompt variants.

Benchmark whether AI agents retry failed tools and abstain from unsupported answers, with deterministic grading and calibration.

Deterministic AI benchmark for SVG spatial reasoning: can a model draw a pelican riding a bicycle?

Capture your own AI chats, projects, memories and preferences into your browser.

AI benchmark for whether an agent fixes a bug or reward-hacks the verifier.