MCP server Claude CodeCodexCursor
Vendor-neutral local-LLM-inference benchmark and hardware-config advisor for omlx and llama.cpp -- measures real tokens/second on your own hardware, live. Runs locally from the inferbench-cli Python package.
MCP server Claude CodeCodexCursor
Zero-dependency, cross-platform LLM/GEO/AEO checker CLI. 21 checks, pure Python stdlib, no runtime dependencies. Runs locally from the llmscout-cli Python package.
MCP server Claude CodeCodexCursor
Mastery Measurement API and CLI: fits Bayesian Knowledge Tracing (BKT) and Item Response Theory (2PL IRT) models to learner response logs and reports per-learner, per-skill mastery estimates. Runs locally from the masterytrace-cli Python package.
RudrenduPaul/podcast-guest-crm
MCP server Claude CodeCodexCursor
Manage podcast guest pipeline, outreach drafts, and analytics via 5 MCP tools. Runs locally from the podcast-guest-crm-cli npm package.
MCP server Claude CodeCodexCursor
Scan a dataset or model directory for PII and secrets, redact what you find, and package a public-release bundle with a Hugging Face dataset/model card and an EU AI Act Art. 53(1)(d) training-data summary -- generated from the scan, not hand-written. Runs locally from the releaseguard-cli Python package.
MCP server Claude CodeCodexCursor
Scores AI-generated UI for genericness ("slop") using an Anthropic LLM-judge rubric, with a --json mode for CI/agent quality gates and a documented programmatic API (scorecomposite, ScoreInput, LLMJudgeSource) for in-process use by agent frameworks. Runs locally from the slop-eval-cli Python package.
RudrenduPaul/swarm-rd-orchestrator
MCP server Claude CodeCodexCursor
Ray-native context/memory sharing for parallel research agents, with an agent-native CLI and MCP server (Milestone 1 spike). Runs locally from the swarm-rd-orchestrator-cli Python package.
MCP server Claude CodeCodexCursor
Shared-context and memory coordination server + CLI for swarms of parallel AI agents, speaking the SwarmMesh v1 protocol (HTTP + WebSocket + MCP), interoperable with the Node implementation. Runs locally from the swarmmesh-cli Python package.
MCP server Claude CodeCodexCursor
Self-hosted event server that pushes a notification the instant a parallel coding-agent session blocks, needs review, fails, or finishes. Runs locally from the taskswarm-cli Python package.
MCP server Claude CodeCodexCursor
Compare AI coding tool spend before and after a migration -- Cursor, Claude Code, GitHub Copilot, OpenCode, and Codex CLI, real numbers pulled from each vendor's own API or local logs, one command, zero runtime dependencies. Runs locally from the teamspend-cli Python package.
MCP server Claude CodeCodexCursor
Runtime governance middleware for AI agent tool calls -- gate shell, filesystem, network, and credential access before a tool executes. Runs locally from the toolgovern-cli Python package.
MCP server Claude CodeCodexCursor
Provenance-first OSINT/security intelligence feed CLI. Every item ships a real source URL, a real timestamp, and an explicit live/fallback flag -- never a fabricated or silently-replayed data point. Runs locally from the truesignal-cli Python package.
MCP server Claude CodeCodexCursor
Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP. Runs locally from the truthroute-cli npm package.
MCP server Claude CodeCodexCursor +2
Vendor-neutral CLI and MCP server that verifies the token and cost savings AI-coding-agent context-reduction proxies (rtk, headroom) actually deliver, measured against a real 23-task labeled corpus with a local tokenizer instead of the proxy's own claimed. Runs locally from the tokentrust-cli npm package.
MCP server Claude CodeCodexCursor
Classify a GPU workload as inference or training from telemetry alone, no application changes required. Runs locally from the workloadtruth-cli Python package.
MCP server Claude CodeCodexCursor
Per-workspace usage metering and fail-closed quota caps for shared self-hosted AI assistant deployments (Odysseus and compatible backends). Genuine independent Python port with the same CLI and --json shapes as the npm package. Runs locally from the workspaceguard-cli Python package.
MCP server Claude CodeCodexCursor
Provider-agnostic CLI and MCP server that signs, hash-chains, and verifies compute usage receipts (GPU-hours, workload type, hardware) so any third party can audit them without trusting the issuer. Runs locally from the computeledger-cli Python package.
RudrenduPaul/agent-observability
MCP server Claude CodeCodexCursor +2
AI agent observability with deterministic record/replay — capture any LangGraph or OpenAI Agents SDK run, replay it offline at zero API cost. Runs locally from the agent-observability-trace-cli Python package.
MCP server Claude CodeCodexCursor +2
Verifies Ed25519-signed attestation records and builds audit reports via MCP tools. Runs locally from the paceproof-cli npm package.
RudrenduPaul/freelancer-payment-protection
MCP server Claude CodeCodexCursor +2
Command-line client for freelancer-payment-protection: automated invoice escalation, legal document generation, and client risk scoring for freelancers. Runs locally from the freelancer-payment-protection-cli Python package.
MCP server Claude CodeCodexCursor +2
Verify that a GitHub issue closed as "fixed" actually has a merged fix. Catches security issues marked fixed whose PR was never merged. Runs locally from the shimguard-cli Python package.
MCP server Claude CodeCodexCursor +2
PyPI wrapper for TenantGuard, a tenant-isolation security-audit CLI for self-hosted multi-tenant AI-agent platforms. Downloads and runs the official prebuilt Go binary from GitHub Releases, Sigstore-verified on first run. Runs locally from the tenantguard-cli Python package.