Discover the Best AI Tools

Hooks for Claude Code and Codex use configurable rules and Jev verification to warn or block tool calls and stopping decisions. They require service credentials and fail open when verification fails, including authentication problems; agent-editable rules and model judgments are not a hard security boundary.

A Node.js CLI and MCP server exposes Jev-based classification, choice, routing, ranking, semantic line filtering and action checks. It requires an API key and sends selected text to the service; clipped context can miss relevant lines, and its guard is advisory rather than a security boundary.

An experimental protocol repository includes runnable offline tools for replaying metrics on a fixed historical 40-case evaluation and checking protocol fixtures. It supplies no runtime agent controller or live API evaluation, and the original model responses are unavailable; the replay is not a general-purpose evaluator.

A TypeScript library adds logged, threshold-based decision gates across requirements, planning, execution review and release workflows. The implemented backend uses a compatible LLM provider and needs its credentials; the Jev backend is currently a contract stub rather than a working integration.

An experimental Hermes plugin produces model-routing plans from an operator-defined allowlist and budget constraints, optionally using Jev. It does not dispatch requests or switch models automatically; external calls are off by default and reported fixtures are synthetic, not evidence of live savings or quality.

A prototype GitHub Action turns trusted issues into proposed fixes using an agent, repository checks, a read-only reviewer and Jev decision gates with bounded retries. It opens pull requests without merging; provider credentials are required and its Claude spending cap excludes Jev charges.

A Python loop combines Jev probabilities with operator-supplied priors to propose agent workflow actions from supplied state. It requires an API key and prepared questions; the small included benchmark does not establish an improvement over raw Jev.

Savvly MCP exposes Savvly product information, eligibility checks, comparisons and illustrative retirement projections to AI clients. Public access needs no account; projections are scenarios rather than guaranteed returns, and the hosted endpoint records anonymous usage analytics.

PayPerByte MCP discovers data feeds and buys responses through x402 using real Base-mainnet USDC; stream subscriptions use a separate testnet layer. Receipts attest delivered bytes, not factual correctness, and the documented fact-oracle query has no active publisher yet.

BORME MCP queries Spanish company-registry events, timelines, daily summaries and derived signals. Its hosted service is read-only with capped results and partial tax-ID coverage; self-hosting requires a separately populated PostgreSQL dataset.

Bizdays calculates business dates with bundled public-holiday calendars and country weekend rules through a library or MCP. Verification coverage varies; some countries have weekend rules but no holiday calendar, and company closures must be supplied separately.

Blank Invoice Maker MCP builds prefilled invoice-editor links and lists templates for browser review and PDF download. Invoice data is encoded in the URL fragment rather than uploaded by the tool; the link itself carries the invoice and still needs review before use.

NodeFlare MCP gives agents EVM-chain RPC queries, wallet reports, logs and transaction simulation. Basic reads are keyless and rate-limited; heavier methods need a key or x402 wallet, which can automatically pay real USDC when a request requires payment.

Multichain MCP exposes balances and prices across Stacks, Celo and Base, with portfolio aggregation and unsigned transfer or token-deployment preparation on paid tiers. Users sign transactions externally; basic queries use public endpoints and advanced functions need a license.

DataSaudi MCP lets agents discover and query Saudi headline statistics from the public DataSaudi API in English or Arabic without a key. Most geography stops at provinces; property figures are indices, not transaction prices, and it does not cover all Saudi government datasets.

SwapTitan offers API and MCP access to crypto prices, routes, quotes and unsigned swap transactions for Solana and supported EVM chains. Wallet signing remains external; free API access still carries transaction routing/network fees and rate limits.

Payfetch is a local MCP server and CLI that fetches paid x402 URLs under operator-defined spending and host policies. It needs a wallet signer, currently supports exact-scheme Base USDC only, and can spend real funds; Windows and other payment rails are unsupported.

This Hermes adapter uses Jev to remove or truncate stale tool history while retaining ordinary conversation text and protecting specified state-changing calls. It reads the session database without writing back and optionally exports JSON. Setup builds an upstream library; a TypeSafe key is required, context is sent externally, and relevance judgments can miss useful evidence.

check-risk combines repository policy rules with optional Jev semantic analysis to score Git changes and recommend checks and reviewers. It runs locally as a CLI or GitHub Action; semantic mode sends code context externally. Live Jev validation remains pending, offline results are incomplete, and risk scores are not failure probabilities.

Frost analyzes a prompt with TypeSafe Jev and locally recommends a configured model, harness and effort level according to cost, quality or speed policy. It does not launch the recommended model. A key and maintained catalog are required; example rankings and optional capacity snapshots do not guarantee account access or outcomes.

pi-typesafe-jev exposes TypeSafe choice, yes/no, score and batched judgments as Pi tools, including reusable question files. Calls send supplied state to the API; users retain responsibility for thresholds and actions. The setup stores the API key in plaintext locally and its input is not masked.

pi-jev-code adds Jev search ranking, pre-edit semantic checks and baseline-to-current diff review to a single Pi coding agent. It needs Pi, Node.js and a TypeSafe key and sends task/code context for judgments. Thresholds remain heuristic; API failures allow continuation and final reviews occur after the agent's edits.

JevKeep preserves selected verbatim conversation excerpts alongside Codex's normal compaction summary using Jev relevance scoring. It requires supported compaction hooks, Node.js and a TypeSafe key; conversation and tool text are sent externally. Excerpt size is capped, selection can miss details, and failures leave native compaction running.

decide-mcp is a local stdio server that delegates bounded choices to configurable models and policy profiles, defaulting to Jev through AI Gateway. Model calls require provider credentials and send context remotely. It distinguishes native distributions from model-estimated percentages; recommendations do not execute actions or guarantee calibrated confidence.