Web step blocked? Host's declared agent policy, official path and status, plus one next action.

Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.

Permission-aware retrieval for AI systems: policy-enforced access to organizational knowledge.

The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches

Manage the DeepSeek Harness skill catalog from Settings: list what DSH actually resolves, enable or disable a skill by policy without touching its source file, read and edit SKILL.md, and create, import, or permanently delete skills.

A DeepSeek Harness plugin for Assistant Policy.

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

Free website privacy scanner for pre-consent cookies, trackers, consent, policy, and HTTPS/TLS.

Workit Claude Code plugin — session and per-turn task context, branch policy on git shell commands, workit method skills, and verifier/reviewer/implementer agents

Model Context Protocol server transport: serve typed procedures as MCP tools to Claude and other MCP clients, with streaming progress, list_changed and an expose policy.

Enables AI agents to drive policy evaluation over MCP by starting executions, answering policy questions from case evidence, and reading deterministic outcomes with reasoning traces, while the runtime controls which questions are asked and how answers combine.

Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.

SceneScout — exploratory UI testing for AI coding agents. An MCP server that gives any agent (Claude Code, Cursor, VS Code Copilot, Codex, Gemini CLI and others) a structured view of a running web app, always-on oracles, a network-level write policy, memo

Enables AI agents to make policy-scoped payments with spending caps, recipient allowlists, approval thresholds, instant revocation, and an append-only audit trail in a sandbox wallet.

Enables MCP clients to query a sensitive local workspace through a read-only status bridge that returns only pre-defined numeric file counts, status enums, and static policy—never source, paths, diffs, logs, environment variables, or command execution.

A gateway MCP server that lets agents reach any upstream MCP server through one endpoint while enforcing policy rules, holding risky tool calls for human approval, containing prompt-injected sessions, and logging every call.

Enables AI agents to build, validate, and submit ledger-native XRPL transactions against public nodes — escrows, XRP and token payments, DEX/AMM swaps and liquidity, issuer clawback, and x402 pay-per-request — with validated-ledger proof of results. State-changing calls go to the account owner for browser signing, while an owner-funded agent account allows autonomous spending bounded by on-ledger balance and local policy limits.

Enables Claude to answer plain-English questions by listing and describing database tables, running read-only SQL queries, and searching a folder of policy documents.

Evaluates proposed x402 payments against a local policy and returns pay, review, or do_not_pay, while also listing and evaluating outstanding authorizations to flag double-pay or limbo risk.

Exposes a single authenticated MCP endpoint that federates to agents running on your own machines, letting you delegate coding jobs to be worked in fresh git worktrees and pushed to a branch, or proxy the stdio MCP servers installed there as tools. Agents dial out through a Cloudflare Tunnel and enforce your local policy, so no inbound ports are opened.

Reflect2Evolve memory plugin: layered L1/L2/L3 memory, reflection-weighted value backprop, cross-task policy induction, skill crystallization, and three-tier retrieval for OpenClaw, Hermes Agent, and DeepSeek Harness.

Zero-custody DeFi intelligence and control MCP server for AI agents, exposing Trail Heat, wallet and risk intelligence, swap and futures workflows, x402 access, and policy-gated execution. FarmDash never receives customer private keys.

Exposes agent-facing tools that let a personal AI agent submit each proposed action for an allow, require_approval, or deny verdict against OWASP PAA10 policy rules, plus tools to record provenance-tagged memories, log refusals, read status, and trigger a self-stop. Its decisions are advisory unless paired with the project's gating proxy or hook, which enforce them.