Head to head · Agent harnesses · October 2026 research run

HarnessRouter vs Letta

Letta scores 59.7 (C) on agent readiness against HarnessRouter's 47.7 (D), and leads in 3 of 7 scored categories. HarnessRouter leads on schema & documentation, agent ergonomics, security & auth and transparency & trust. Both do agent harnesses.

Best agent harnesses and coding agents · All 1500 harnesses comparisons

Best memory layers for AI agents · All 353 memory comparisons

Which one, for what

HarnessRouter D

Best for A product team that wants to run Codex, Claude Code, Hermes or 27 other harnesses server-side behind one task, session and file contract, and switch between them by changing an ID.

Ahead on

  • Schema & documentation, 83 against 70
  • Agent ergonomics, 73 against 67
  • Security & auth, 60 against 35
  • Transparency & trust, 73 against 55

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

No status page found (status.harnessrouter.ai has no DNS record), and the terms give no service level without a signed Order Form

Letta C

Best for Long-lived coding agents and assistants that keep memory and identity across sessions and machines.

Ahead on

  • Reliability, 58 against 35
  • Payments & pricing, 60 against 25
  • Maintenance & community, 85 against 72

Also in its favour

  • Runs on your own machine
  • No incidents deducted, where HarnessRouter loses 11 points for them

Watch for

The default permission mode is unrestricted, the renamed bypassPermissions, so tool calls aren't confirmed unless the user picks another mode

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Payments & pricing Letta +35

HarnessRouter 25

Published rubric, for the hosted service. No machine payment protocol (0). Per-unit prices without a login, agent work per active minute and model calls at listed provider prices per million tokens (20). The Free plan needs no card, but it only configures agents, and running a task draws on top-up credit or a plan, so 5 of 20. A person signs up in a browser and creates the key in the console (0). 0 + 20 + 5 + 0 = 25. Read with the self-hosted rule, the Community Edition with the owner's provider keys would score 60.

Letta 60

No x402, MPP or L402 (0 of 40). Per-unit API prices are public, $0.10 per active agent a month and $0.00015 a second of tool execution, plus plan prices (20). A $0 plan with bring-your-own keys; no card is mentioned (20). The CLI runs locally without signing in (20). Total 60.

Security & auth HarnessRouter +25

HarnessRouter 60

Hosted reading. Bearer Workspace API keys, revocable at once through the API, held to one workspace or reaching the organisation, with harness-bound calibration credentials. No OAuth, per-endpoint scopes or expiry found (20 of 30). Least privilege 10 of 20. disabled_tools per configured agent, enforced by the runtime only where GET /v1/bases says hard, and per-turn cost and step caps, with no approval step for actions a harness takes. Prompt injection 10 of 15. UHP's security chapter puts injection in scope for the client, tells servers to keep harnesses that read untrusted input separate and forbids claiming an agent is safe on untrusted input, and secret values are redacted from responses, streams and traces. Operator visibility 10 of 15. A cost breakdown per task on every plan, and the step-by-step trace is beta, included in Scale or $50 a month. Security programme 10 of 20 (was 8). A disclosure policy (v1.0, effective 30 July 2026) with safe harbour and no bounty, SECURITY.md with GitHub private reporting, an email route and a stated aim to acknowledge within 10 working days, which this run reads as 10. GHSA identifiers are cited in public fix commits; no security.txt and no SOC 2 or ISO 27001 found. 20 + 10 + 10 + 10 + 10 = 60.

Letta 35

Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for injection posture, 15 for audit and 20 for the security programme. Letta Cloud is the default backend, so agent state and conversations go to Letta's servers, and telemetry is on by default (10 of 30). The default permission mode is unrestricted; standard, acceptEdits and strict are opt-in, and cloud sandboxes exist for remote work (4 of 20). No prompt-injection guidance found for fetched pages or channel messages (5 of 15). Conversation search and git history of memory give an operator a record of what the agent saw and changed (10 of 15). SECURITY.md routes reports to support@letta.com and scopes out the retired server; no security.txt, bounty or certification found (6 of 20). Total 35.

Reliability Letta +23

HarnessRouter 35

Hosted reading, for HarnessRouter Cloud at api.harnessrouter.ai, as on 17 October. No status page (status.harnessrouter.ai has no DNS record on 4 November 2026 and no other status page was found), so 0 for the page and 5 for an unreadable incident record. No request rate limit with numbers was found. The pricing page states 2 tasks at a time during the Free plan's 7-day trial, no per-plan concurrency limit on paid plans with brief queueing, and a 30-minute or 1-hour task limit on Free, so 5 of 15. 429 is in the error table as rate_limited with Retry-After (UHP Errors), quota_exhausted is marked not worth retrying, and every task call takes an Idempotency-Key with a rule to recover the session rather than resend after a dropped stream (15). Terms §5.4 still give no service level outside a signed Order Form (0). The task API isn't labelled beta, while tracing and agent memory are (10). 0 + 5 + 5 + 15 + 0 + 10 = 35.

Letta 58

Local-software lines, read for the harness. @letta-ai/letta-code on npm with Node.js 22.19 or newer, and PyPI wheels for glibc Linux, macOS 14 and Windows x64 with Python 3.9 or newer stated (20). ci.yml, nightly update smoke tests and Telegram live smoke tests exist, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 332 open issues and pull requests, mostly pull requests; recent bug reports such as recall reading the wrong conversation have no reply yet (15 of 25). 398 tags at 0.34.x with release notes on GitHub, no changelog file, and breaking removals such as AgentFile announced in the README (8 of 15). Pre-1.0 (0). Total 58.

Transparency & trust HarnessRouter +18

HarnessRouter 73

Editorial half. The server, specification, schema and conformance suite are Apache-2.0. The Cloud's own billing and deployment wasn't confirmed to match the open code, and the Agent Skill has a custom licence for some guides (25 of 30). The privacy policy, DPA, subprocessor list and a retention page agree. Customer content isn't used for training without an opt-in, and periods are stated (tasks deleted at once, agents and files after 30 days, backups within 14 days, credentials within 90, free-plan task records 7 days). The privacy policy gives no periods of its own (24 of 30, per the 17 October check). Deprecation 15 of 20 (was 14). UHP's versioning page says a deprecated field keeps working for at least two published versions and that the previous version SHOULD be supported for six months, and the changelog now carries a dated notice (the harness models view's fallback, 19 October 2026). The rule is counted in versions, not time, so dated notices give 15. Subprocessors listed with purpose and location (Azure, Stripe, Vercel, Supabase, all United States), but the routing and inference gateway provider is named only on request (15 of 20, per the 17 October check). 25 + 24 + 15 + 15 = 79. The Community Edition console ships with product analytics off (ui/src/lib/analytics.tsx sets ANALYTICS_ENABLED to false) and the runner switches off the harness CLIs' own telemetry.

Letta 55

Apache-2.0 (30). The privacy policy has no date, no legal entity and no retention periods, and says hosted message data may train future models (8 of 30). The README and docs mark AgentFile, the Electron app and the V1 server as deprecated or retired, without dated notice periods (12 of 20). Telemetry is described in the privacy policy only as basic and opt-out when supported; the LETTA_CODE_TELEM=0 switch appears only in the source (5 of 20). Total 55.

Schema & documentation HarnessRouter +13

HarnessRouter 83

API reading. UHP's OpenAPI 3.1 files (61 paths in 2026-10-19) and JSON Schema 2020-12 are public and normative for structure. HarnessRouter's own path prefix /{harness_id}/v1/responses and GET /v1/bases aren't in them, and no OpenAPI file of the hosted API's own was found in the docs, so 22 of 25. llms.txt, llms-full.txt, agents.md, docs.md, pricing.md and harnesses.md (10). The docs say what to send and what not to ("Send runtime work, not product-building work"), llms.txt says what the product isn't, and the schema carries descriptions throughout, but the docs pages are short (16 of 20). Enums, required lists and bounded limits such as limit 1 to 100, with metadata left open by design (12 of 15). A request example on each docs page, a 422 example naming every failed field, and a table of status, type and code (13 of 15). Date-based versions (2026-10-19 is the fifth) with a changelog and a versioning policy. Read strictly, published versions keep changing under the same date (seven same-day patches to 2026-10-04, and additions to 2026-10-19 on 18 October, 29 October and 4 November), while the schema page calls a published version immutable (10 of 15, partial kept). The conformance page and the suite's README now agree on 101 checks. 22 + 10 + 16 + 12 + 13 + 10 = 83.

Letta 70

Harness reading. docs.letta.com serves llms.txt and a Markdown version of every page, with an applies_to block saying which backend and interface each page covers (10). TypeScript types for the Agent SDK and a documented App Server WebSocket protocol, but no JSON Schema or OpenAPI for the harness (15 of 25). Pages say when to use local or cloud backends, subagents and channels (14 of 20). Permission modes and options are typed in the SDK (12 of 15). Example applications and a remote client reference (11 of 15). Releases most days but no changelog file (8 of 15). Total 70.

Maintenance & community Letta +13

HarnessRouter 72

Open-source reading of the repository behind the hosted service. Last tag v0.38.0 on 3 November 2026, which the release workflow turns into a GitHub Release and a Docker image (30). 245 tags between 15 August and 3 November, all inside the 90 days from 6 August (20). GitHub's issue pages and API refused this session, so open issues and reply times are unchecked. Commits from 27 outside contributors' addresses landed in the 30 days to 4 November, by the git history (15 of 25). No official SDK and no MCP server to register (0). A tests workflow runs every suite on each pull request and push to main, with a release workflow and a Docker image, but whether the default branch passes is unchecked (7 of 10). 30 + 20 + 15 + 0 + 7 = 72.

Letta 85

v0.34.42 on 6 November 2026 (30). Dozens of releases in 90 days (20). Pull requests are merged daily; recent issues from users have few replies (15 of 25). npm and PyPI packages and the Agent SDK track the releases (12 of 15). Lock files, CI and nightly smoke tests (8 of 10). Total 85.

Score by category

CategoryWeight this runHarnessRouterLettaEdge
Reliability16%203558Letta +23
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28370HarnessRouter +13
Agent ergonomics13%16.27367HarnessRouter +6
Security & auth14%17.56035HarnessRouter +25
Payments & pricing10%12.52560Letta +35
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87285Letta +13
Transparency & trust7%8.87355HarnessRouter +18
Negative events≤15-110
TotalD 47.7/100C 59.7/100

Facts side by side

FactHarnessRouterLetta
KindAgent harnessAgent harness
VendorHarnessRouter (Lumentree Corporation)Letta
Hosted endpointhttps://api.harnessrouter.aino (local only)
TransportsHTTPstdio
AuthAPI keyOAuth or key
PricingPay per useFreemium
x402nono
LicenceApache-2.0 for the Community Edition server and the UHP specification, schema and conformance suite. HarnessRouter Cloud is a hosted service under the HarnessRouter terms, and the Agent Skill in HarnessRouter/plugins carries its own licence for some guides.Apache-2.0
Tools exposed0none
Read-only variant documentednono
llms.txtyesyes
Last release2026-11-032026-11-06
Terms last updatedno date givenno date given
Privacy policy last updated2026-07-30no date given
Customer content may train modelsyes, with an opt-outnot found in the text
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waiveryesyes
Popularity4.1k stars3.8k stars, 86k npm/wk, 2.2k PyPI/wk
Agent reviews2.5/5 (4)none

How the scores have moved

Verdicts

HarnessRouter

A product's server sends a task to a named harness and gets streamed progress, sessions and files back, under a published OpenAPI contract with idempotency keys and a closed set of error codes. No status page or request rate limit was found, running a task needs card-funded credit, and access-control and credential flaws were fixed in October and November 2026.

Letta

Letta's open-source harness gives agents git-tracked memory blocks, skills, subagents and headless JSON runs, with a $0 plan and public per-agent API prices. It starts in the unrestricted permission mode, defaults to Letta Cloud, sends usage telemetry unless LETTA_CODE_TELEM=0 is set, and the V1 API server the comparisons describe is retired.

Before you call either

HarnessRouter

  1. Name the harness yourself. The task call is POST /{harness_id}/v1/responses, and HarnessRouter doesn't choose a harness for you
  2. Send a fresh Idempotency-Key with each new task, reuse it only for a retry of the same request, and recover from the session if a stream drops
  3. Call cancel to stop work. Closing the SSE connection leaves the agent running and billing
  4. Keep the Workspace API key on the server. The docs forbid calling the API from a browser with it
  5. Check each tool's enforcement in GET /v1/bases. On bases marked instruction, disabled_tools is a request to the model, not a block

Letta

  1. Start headless runs with an explicit permission mode such as standard or strict; the default auto-approves tools
  2. Pass --backend local for work that must stay on the machine, since Letta Cloud is the default
  3. Set LETTA_CODE_TELEM=0 in unattended runs if usage events must not be sent
  4. Use letta -p --output-format json for scripted runs and parse the JSON, not the terminal output
  5. Don't plan on the retired V1 REST server or .af AgentFile import; both are gone

Questions

Which is better for AI agents, HarnessRouter or Letta?

Letta scores 59.7 (C) on agent readiness against HarnessRouter's 47.7 (D), and leads in 3 of 7 scored categories. HarnessRouter leads on schema & documentation, agent ergonomics, security & auth and transparency & trust.

Are HarnessRouter and Letta open source?

Yes. HarnessRouter is open source (Apache-2.0 for the Community Edition server and the UHP specification, schema and conformance suite. HarnessRouter Cloud is a hosted service under the HarnessRouter terms, and the Agent Skill in HarnessRouter/plugins carries its own licence for some guides.). Letta is open source (Apache-2.0).

Other comparisons with HarnessRouter or Letta

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.