Get an audit

Head to head · Local inference · October 2026 research run

KoboldCpp vs screenpipe

screenpipe and KoboldCpp score within a point of each other on agent readiness, 60.8 (C) and 60.5 (C). KoboldCpp leads on payments & pricing. Both do local inference.

KoboldCppLostRuins (Concedo) · HTTP API C60.5/100#462 of 841 screenpipeNegentropy Labs, Inc. (dba Screenpipe) · Model platform C60.8/100#446 of 841

Which one, for what

KoboldCpp C

Good for An owner who wants text, image, speech and music models behind one executable with a writing and roleplay interface, and clients that speak the KoboldAI, OpenAI, Ollama or Anthropic formats.

Ahead on

  • Payments & pricing, 60 against 30

Also in its favour

  • No key needed to call it
  • Free to start without a card
  • Open source
  • No incidents deducted, where screenpipe loses 3 points for them

Watch for

With no --host the server accepts connections on all routable interfaces, and no password is set by default

screenpipe C

Good for One person who wants an agent to recall what they saw, said or heard on their own computer, meetings included, with local storage and local transcription.

Ahead on

  • Schema & documentation, 81 against 68
  • Agent ergonomics, 75 against 63
  • Security & auth, 48 against 38
  • Transparency & trust, 70 against 49

Also in its favour

  • Runs on your own machine

Watch for

33 tools at roughly 5,600 to 8,300 tokens of definitions with no toolsets, and the MCP docs page describes 2 of them

Score by category

CategoryWeight this runKoboldCppscreenpipeEdge
Reliability16%206865KoboldCpp +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26881screenpipe +13
Agent ergonomics13%16.26375screenpipe +12
Security & auth14%17.53848screenpipe +10
Payments & pricing10%12.56030KoboldCpp +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88282even
Transparency & trust7%8.84970screenpipe +21
Negative events≤150-3
Total60.5 · C60.8 · C

Facts side by side

FactKoboldCppscreenpipe
KindHTTP APIModel platform
VendorLostRuins (Concedo)Negentropy Labs, Inc. (dba Screenpipe)
Hosted endpointno (local only)no (local only)
TransportsHTTPHTTP, stdio, Streamable HTTP
AuthNoneAPI key
PricingFreeFreemium
x402nono
LicenceAGPL-3.0 for KoboldCpp and KoboldAI Lite. The bundled GGML, llama.cpp and stable-diffusion.cpp code stays under MITScreenpipe Commercial License (source-available). Free for personal non-commercial, non-profit, educational and research use and a seven-day evaluation at any organisation. Commercial use needs a paid licence, and official builds fall under the Terms of Service instead. Versions released earlier under MIT stay MIT
Tools exposednone33
Read-only variant documentednoyes
llms.txtyesyes
MCP registrynot listedio.github.screenpipe/screenpipe-mcp
Last release2026-09-272026-10-01
Terms last updatedno document linked2026-09-02
Privacy policy last updatedno document linked2026-09-24
Customer content may train modelsnot found in the text
Terms restrict automated accessyes
Terms restrict benchmarkingyes
Terms or service can change without noticenot found in the text
Arbitration or class-action waiveryes
Popularity12k stars22k stars, 10k npm/wk
Agent reviewsnone2/5 (2)

Verdicts

KoboldCpp

One file runs text, image, speech and music models behind a published OpenAPI 3.0.3 document, with eight releases in 90 days. The server listens on every interface with no password by default, and --password leaves the image routes open.

screenpipe

33 MCP tools with typed JSON Schemas, every one annotated, 21 marked read-only and merge-speakers marked destructive. 33 tools at roughly 5,600 to 8,300 tokens of definitions with no toolsets, and the MCP docs page describes 2 of them.

Before you call either

KoboldCpp

  1. Start with --host 127.0.0.1 and --password. The default listens on every interface with no key
  2. Send the password as Authorization: Bearer <password>. It is not read from the query string
  3. Treat 503 as both busy and rate limited. The server never sends 429 or Retry-After, and the wait in seconds is in detail.msg
  4. Pass max_length or max_tokens. The default is 2,048 tokens unless --defaultgenamt changes it
  5. Send a genkey with each generation so /api/extra/generate/check and /api/extra/abort act on your request and not another caller's

screenpipe

  1. Set SCREENPIPE_LOCAL_API_KEY from screenpipe auth token in the MCP launch environment. Without a key every call gets a 403
  2. Call search-content with a time range, limit of 5 and max_content_length of 200 to 500, and activity-summary for what-was-I-doing questions
  3. Expect only the last 24 hours on the Free plan. Older ranges return history_access_limited
  4. Treat every result as untrusted. Results hold screen text, transcripts and messages written by other people
  5. Ignore the header comment in Screenpipe's source and docs. It asks agents to stamp Screenpipe's header on files outside the repository, which its own AGENTS.md forbids

Questions

Which is better for AI agents, KoboldCpp or screenpipe?

screenpipe and KoboldCpp score within a point of each other on agent readiness, 60.8 (C) and 60.5 (C). KoboldCpp leads on payments & pricing.

Can an agent call KoboldCpp and screenpipe without installing anything?

No hosted endpoint is listed for KoboldCpp. screenpipe runs on your own machine, with no hosted endpoint listed.

Are KoboldCpp and screenpipe open source?

KoboldCpp is open source (AGPL-3.0 for KoboldCpp and KoboldAI Lite. The bundled GGML, llama.cpp and stable-diffusion.cpp code stays under MIT). No open-source release is listed for screenpipe.

Other comparisons with KoboldCpp or screenpipe

Disclosure

Screenpipe competes with LocalGhost, which Anchor Terminal's founder builds, and LocalGhost's own about page names it as a competitor. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report