MCP server that checkpoints long agent tasks: roll back to any step, resume in a new session.
AI & ModelsLocal
Loading MCP servers…
Showing 1,729–1,776 of 2,642
MCP server that checkpoints long agent tasks: roll back to any step, resume in a new session.
Showing 1,729–1,776 of 2,642
Local-first AI memory MCP server. Record, recall and consolidate memory on your own machine.
Read your DrawOffer resumes, saved jobs and applications from Claude, Cursor and other AI tools.
QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)
Discover articles about AI-assisted development and agent workflows.
6-category AI readiness, Schema.org, robots.txt, /llms.txt & 25k-token audit + auto-fix MCP server
Compare AI perspectives with configurable Modes, estimate deliberations, and retrieve run receipts.
MCP Server for Agent Reputation & Trust Scoring
Local, reversible pseudonymisation of client files for Claude, ChatGPT and Copilot.
Raily personal-agent MCP with scoped reads and approved actions.
Search a directory of software an agent can adapt or operate, by need, license or interface.
Persistent memory for Claude via weighted, interconnected knowledge nodes.
Multi-agent literature review: research, peer review, and synthesize grounded reports.
Run a golden set and gate LLM model swaps on accuracy, with latency and cost per request.
Version control for fleets of coding agents: isolated workspaces, status, diff and history.
Typed decision tools for AI agents, powered by TypeSafe Jev.
Host-neutral MCP bridge for TypeSafe AI Jev judgments with typed review, routing, and gate tools.
Humanize AI text and check AI-detection scores from Claude, Cursor, or any MCP client.
Role-aware Agent memory with cross-session recall, durable writes, and multi-Agent project scope.
Make audiobooks locally with Kokoro voices from your AI assistant. Nothing leaves your computer.
Test whether AI agents retain critical instructions as conversations grow.
Live LLM pricing, context windows and model ids, read from each vendor's own page every 3 hours.
Redacts PII/PHI from text before it reaches an LLM. Fail-closed, self-hosted, no egress.
Decision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk.
Find out which MCP servers you actually use: local, read-only audit of Claude Code transcripts.
Negotiation math engine. Pareto frontier, counteroffer generation, zero LLM tokens.
Check if an AI agent is trustworthy. Sybil detection, signed attestations, 150,000+ agents. Free.
Context selection and compression for AI agents - recall measured, not claimed.
Self-curating agent memory kept honest by survival-based selection over measured outcomes.
138-tool MCP server for AI agent firms: security, A2A, Hebbian memory, fleet mgmt
Web grounding for local & cloud LLMs: search, fetch, token-capped evidence packs, and research.
Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.
Append-only event log for cross-agent context/memory sharing via 3 MCP tools.
Multi-agent context sharing, memory, and status coordination via MCP tools.
Wraps the taskswarm CLI as a single generic MCP tool for multi-agent task coordination.
Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.
Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.
Runtime budget authority for AI agents — reserve, enforce, reconcile spend across providers
Operator-as-agent MCP hub. 6 tools. First $5 free, then $0.001/call.
Claude Desktop reminders for Windows. Survives MSIX boundary; persists across restarts. Zero deps.
Per-client shared AI memory: approved notes that Claude, ChatGPT and Cursor read over MCP.
Review, edit, and approve AI agent task plans in a ComfyUI-style visual node editor in your terminal
Find MCP servers for ESP32, Arduino, 3D printers, Home Assistant, cameras and other hardware.
Read-only MCP server for the OPERANT AI operating-agent calibration benchmark.
Agentic pipeline orchestration MCP server for AI-driven development workflows.
Offline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network.
MCP server exposing Dify knowledge base retrieval to Cursor and other MCP clients
