Claude
- Open Add custom connector ↗
- Name it Telarch and paste the URL
- Click Add, then ask away
https://telarch.ai/mcp
Perseus Computing LLC·AI models & tooling·Live in ![]()
Agent memory, budget & audit
Telarch is an open-source (MIT) cognitive infrastructure suite by Perseus Computing LLC for your AI and Codex. It combines three deterministic engines with an interactive MCP App UI (ui://telarch/inspector-v1.html): (1) Harpe uses exact knapsack selection to pack the most important context items under a token budget (pinned items are kept, and an overflow is reported) and returns a SHA-256 policy digest; (2) Kibisis resolves conflicts among the memory records passed in a call across verified, candidate, superseded, and revoked (tombstoned) records, with a scope check, a fencing-token check on the numbers of the call, and <kibisis-recall> framing that escapes stored text; and (3) Argus seals and verifies linear RFC 8785 canonical JSON SHA-256 hash chains over the events passed in a call to find the first event that was changed. Hosted edge calls on https://telarch.ai/mcp execute statelessly: the server stores no memory, lease or ledger between calls.
Open the interactive Telarch Inspector UI to explore knapsack budgeting and SHA-256 audit chains.
https://telarch.ai/mcphttps://telarch.ai/mcptelarch.aiThe AI reads these server instructions before using this connector, every time.
Stateless tools; nothing is stored between calls. Use for exact knapsack token packing (priority 0-100, lower = more important), to resolve the memory records you pass in and frame them in an escaped <kibisis-recall> envelope, / for RFC 8785 SHA-256 audit chains (safe integers and strings only; no fractions), and to show items, records or sealed events of the conversation (built-in demonstration data for a tab that is given none) in an interactive panel. A refused call carries a stable code and the path of the argument at fault: in structuredContent.error for a refusal by a tool, in error.data for arguments that do not match the schema. Arguments are checked against each tool's inputSchema; a call that does not match is refused.
Agent memory, budget & audit. Telarch is an open-source (MIT) cognitive infrastructure suite by Perseus Computing LLC for your AI and Codex. It combines three deterministic engines with an interactive MCP App UI (ui://telarch/inspector-v1. It is listed under AI models & tooling.
Open its listing in the app's connector directory and connect. No sign-in is needed. Step-by-step setup for each app is on this page.
The Telarch MCP server URL is https://telarch.ai/mcp. Paste it as a custom connector in Claude, ChatGPT, Gemini or Grok, or add it to Claude Code, Cursor or any MCP client. Setup steps.
Yes. Telarch is published or run by Perseus Computing LLC, so it is the official MCP server. See other official connectors.
It is listed in 1 store: ChatGPT. Apps where it is not listed can usually still add it as a custom connector.
It is ranked 12,748 of 15,293 in the ChatGPT directory. A rank is the store's own order, not a usage count. How we track ranks.
It has 7 tools: 7 read data. See every tool and its inputs.
No. All of its tools only read data.
It comes with 3 skills. A skill tells the AI how to do one job well with these tools. Read each SKILL.md.
Here are examples from its store listing. Type one into your AI after you connect.
Yes. Some of its tools show an interactive widget in the chat, not only text. See more connectors with interactive UI.
The top-ranked connectors in AI models & tooling include:
This page updates every day. To ask about Telarch from Claude, ChatGPT or a coding agent, connect the Agent Ready MCP server: it tracks ranks, tools and new listings across the AI plugin stores.