Discover the Best AI Tools

Text File Read and Refactor MCP searches, reads and edits text by lines, slices or boundary patterns while preserving encoding and BOM. It is a local Python stdio server; the public repository receives selected development snapshots.

Skillful routes coding prompts to installed skills, MCP servers or commands using a local shortlist and TypeSafe Jev, injecting a small suggestion set through agent hooks. Prompts are uploaded by default. Retrieval targets and task-outcome benefits remain unproven; failures fall back to a reminder without blocking the agent.

jev-scout is a Rust CLI and MCP server that retrieves GitHub and crates.io candidates and uses TypeSafe Jev to rank their relevance and maintenance signals. It requires a TypeSafe key and network access; registry metadata and model scores do not guarantee installability, licensing suitability or absence of errors.

jear is an early Rust client that routes requests toward NEAR AI Cloud models or agent plans using budget, quality and sensitivity policies with optional Jev judgments. Its default demo is offline; live inference needs provider keys and Jev endpoint configuration. The multi-tenant proxy is a design, not an implemented service.

jev-skill-gate scores installed Claude Code skills against project or prompt context and writes visibility overrides to reduce the skill manifest. It supports remote Jev scoring and local fallback; thresholds may hide relevant skills, and published savings or small evaluation results are not general guarantees.

This Pi extension uses TypeSafe Jev to prune old tool calls and results without rewriting ordinary conversation or the session file. It offers background scoring and conservative preservation of side-effecting calls. Context is sent to an external API; errors retain unmodified messages, and pruning can lose useful evidence or increase cache costs.

MCP File Tools lets AI clients read, search and edit legacy-encoded text while preserving original encoding, BOM and line endings. Access is limited to configured directories. Encoding detection is heuristic and exposes confidence; users should check ambiguous files before rewriting them.

hledit-mcp exposes hash-anchored file reads and edits to MCP coding clients, rejecting edits when referenced lines have changed. It requires the separate hledit CLI and Node.js; a stale result requires rereading the file, and workspace scope must be configured.

Agent Coherence coordinates shared state and files across AI agents using versioned reads and conditional writes, with framework adapters and MCP access. Cache coherence alone does not prevent stale writes: agents must use the guarded write interfaces. External side effects remain outside this protocol.

Jev Workbench defines, tests and publishes versioned Jev judgment functions through a local UI, HTTP and MCP with scoped client tokens. Production requires provider credentials and never substitutes simulated answers on failure. Demo answers are simulated; runtime integrations and business accuracy need separate validation.

todo-jev classifies requests into rules, specialist skills or model work using Jev and local presence checks. Routing is implemented, but execution handlers return examples and require your own integration. A passed environment check does not establish skill installation, credentials or successful execution, and routing scores are not calibrated success probabilities.

This skill-router CLI ranks installed Claude Code skills against a session goal and suggests discovery when none fit. Real ranking uses TypeSafe; without a key, labeled mock mode matches keywords. Recommendations do not install or execute a skill, and the integration currently targets Claude Code rather than arbitrary agents.

tiershift uses Jev signals and configurable rules to select a model tier, with CLI, libraries and proxy integration. Completion calls can escalate after provider failure. It needs judge and model-provider access; cost and quality results on plain prompts do not establish performance for long, tool-using agent workflows.

Mastra Jev Moderation is a TypeScript input processor that sends the final message text to Jev and blocks above a configured threshold. History, attachments and outputs are not moderated. A key is required; timeouts, HTTP errors and an open circuit breaker let input through, so independent safeguards remain necessary.

jev-shield proxies stdio MCP traffic, combining structural policies, Jev checks on tool calls/results/descriptions and session taint tracking. It requires an external model service and configurable failure behavior, including fail-open. Probabilistic screening may miss attacks and is not a replacement for sandboxing or human authorization.

typesafe-mod adds Claude Code function hooks that annotate question choices with Jev probabilities and optionally suggest skills. Automatic answers are opt-in, and failures leave normal dialogs intact. The question judge reads options rather than conversation history, skips multi-select questions and requires TypeSafe access; confidence is not user authorization.

jcm-router is a local Claude Code proxy that uses Jev to choose model and effort, with cost guards for switching established conversations. It forwards client authentication and sends selected prompt context to TypeSafe. Switching can rebuild expensive caches; estimates and workload-specific results are not guaranteed savings.

LangChain Skill Router replaces deepagents skill middleware with per-turn selection through a pluggable judge, including Jev. Failures restore the full catalog. Hosted judges receive routing context; token reductions in one benchmark do not guarantee lower cost, latency or preserved task quality elsewhere.

Hermes Jev Plugin gives Hermes Agent tools for binary checks, option routing, rubric scores and mixed evaluations using TypeSafe Jev. It requires a TypeSafe API key and returns structured probabilities rather than chat text; agent workflows must interpret the results.

Jev MCP Dispatcher is a prototype that discovers MCP tools, selects actions with Jev and extracts primitive arguments from command text before executing them. It needs a TypeSafe key and explicitly stated argument values; complex schemas, clarification and full argument validation are not supported.

Prompt2Jev combines an agent skill with a CLI to turn requirements, prompts or existing decision code into typed Jev requests and runnable wrappers. The CLI validates and generates artifacts offline; conversion needs a coding agent and live decisions require TypeSafe credentials.

DSH Jev adds a typed-question Jev tool to DeepSeek Harness profiles. It targets a specific DSH release candidate and requires a TypeSafe key; the agent decides when to call it, and it is neither a streaming chat adapter nor automatic enforcement.

Open Jev Approvals reviews Claude Code tool calls with Jev and applies local allow/deny rules with an audit log. It targets macOS and Linux and needs TypeSafe credentials; missing keys, service errors or a broken audit database allow calls rather than block them.

Pi Heed preserves user rules and task state in ledgers for the pi agent and checks tool calls against them. Jev can judge ambiguous rule scope and changes, while code enforces recorded policy. Model omissions, uncertain judgments and unsupported shell patterns can still miss violations.