Head to head · Agent harnesses · October 2026 research run

dsh-superagent (DeepSeek) vs Letta

Letta scores 59.7 (C) on agent readiness against dsh-superagent (DeepSeek)'s 42.1 (E), and leads in 6 of 7 scored categories. 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

dsh-superagent (DeepSeek) E

Best for Teams on github.com that want a DeepSeek Harness agent to turn allowed people's issue requests into pull requests, run on an isolated machine or OS account.

Also in its favour

  • Free to start without a card

Watch for

Executor and main Sessions run with danger-full-access as the operator's OS user, and the docs say a worker can read the operator's home directory

Letta C

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

Ahead on

  • Reliability, 58 against 15
  • Schema & documentation, 70 against 61
  • Payments & pricing, 60 against 40
  • Maintenance & community, 85 against 34

Also in its favour

  • Runs on your own machine

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.

Maintenance & community Letta +51

dsh-superagent (DeepSeek) 34

Published on 31 October 2026, within 30 days, read as the last published change since no tag or release was found (30). One publication, so not three releases in 90 days (0). Issues, pull requests and Discussions couldn't be read, and the README frames the code as a reference prototype adapted from an internal version (0). No official SDK or registry entry (0). Exact dependency pins and a lockfile, but no CI workflow found, and the docs pin DSH 0.2.1-rc.3 (23 October 2026) while npm latest is 0.2.1-rc.5 (29 October 2026) (4).

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.

Reliability Letta +43

dsh-superagent (DeepSeek) 15

Local-package reading, since it runs as a DSH bundle on the operator's machine. Not published to npm (private: true in package.json, and the registry has no dsh-superagent). It installs from a git clone with pnpm install && pnpm build on top of @deepseek-ai/dsh@0.2.1-rc.3, with Node 22.19+ or 24+, git 2.32+, Python 3.8+, tmux and gh 2.48+ stated, so half credit (10). A vitest suite of about 25 spec files is listed in docs/007, and pnpm check runs the typecheck, tests and build. Two spec files were read on raw.githubusercontent.com. No CI workflow was found at five common paths under .github/workflows, and the directory couldn't be listed (5). Open issues couldn't be read, because github.com and api.github.com weren't reachable from our network. Unchecked, so scored absent (0). Version 0.1.0 with no tag, release or changelog found, so no semver record (0). A research prototype, not stable (0).

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.

Payments & pricing Letta +20

dsh-superagent (DeepSeek) 40

Self-hosted rule, as for the other open-source harnesses. No payment protocol (0). Free under MIT with nothing to buy (20). No card for the software (20). An agent can't get started alone, because the setup needs a person to create a dedicated GitHub user account, accept the repository invitation and run auth login for the wrappers, which SETUP.md lists as operator steps. 0, as the other harnesses that need an account were read (0). The model provider is a separate purchase.

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.

Schema & documentation Letta +9

dsh-superagent (DeepSeek) 61

Framework reading, as for deepseek-harness. No OpenAPI or JSON Schema is published. docs/006 documents the Management API's routes, fields, block shapes and refusals in tables, and the code validates settings with zod (12). Markdown docs in the repository, readable raw, and a SETUP.md written for a coding agent. No llms.txt (5). Nine numbered documents read in order, each stating purpose, limits and what not to do, such as never rerunning the profile-creation command for an upgrade (17). Closed sets for accept mode (off, observe, auto), admission cells, Source states, health states and listen (12). A worked curl example, refusals as 400, 404, 409 and 500 with issues, setup or code, a troubleshooting table and status exit codes 0 to 3 (13). package.json says 0.1.0 and pins an engines.dsh range, but no changelog or tags were found (2).

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.

Score by category

CategoryWeight this rundsh-superagent (DeepSeek)LettaEdge
Reliability16%201558Letta +43
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26170Letta +9
Agent ergonomics13%16.26767even
Security & auth14%17.53335Letta +2
Payments & pricing10%12.54060Letta +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.83485Letta +51
Transparency & trust7%8.85255Letta +3
Negative events≤1500
TotalE 42.1/100C 59.7/100

Facts side by side

Factdsh-superagent (DeepSeek)Letta
KindAgent harnessAgent harness
VendorDeepSeekLetta
Hosted endpointno (local only)no (local only)
Transportsstdio
AuthTokenOAuth or key
PricingFreeFreemium
x402nono
LicenceMITApache-2.0
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-312026-11-06
Terms last updatedno document linkedno date given
Privacy policy last updated2026-09-20no date given
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetnot found in the text
Terms restrict benchmarkingnot read yetnot found in the text
Terms or service can change without noticenot read yetnot found in the text
Arbitration or class-action waivernot read yetyes
Popularitynone3.8k stars, 86k npm/wk, 2.2k PyPI/wk

Verdicts

dsh-superagent (DeepSeek)

The authorization design is careful, with allowed lists, Mandates and a Policy enforced in code, proactive work only recorded by default and auto-merge off. Executors run every command without approval under the operator's OS user, and the README calls it a research prototype with no release, changelog or security policy.

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

dsh-superagent (DeepSeek)

  1. Run it under a dedicated OS account holding only the agent's credentials. Executors run commands without approval and can read the operator's home directory
  2. Set enabled: false on the session-log-deepseek row of the superagent profile before using DeepSeek's official API on private code
  3. Keep the accept mode at observe and the allowed list short until the recorded Decisions look right
  4. Wait for scripts/dsh-superagent status to stop exiting 1 after any save that answers restarting: true before the next request
  5. Send x-orchestrator-request: 1 and a loopback Host to the Management API, and send revision with each PUT, since a stale one gets 409

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, dsh-superagent (DeepSeek) or Letta?

Letta scores 59.7 (C) on agent readiness against dsh-superagent (DeepSeek)'s 42.1 (E), and leads in 6 of 7 scored categories.

Are dsh-superagent (DeepSeek) and Letta open source?

Yes. dsh-superagent (DeepSeek) is open source (MIT). Letta is open source (Apache-2.0).

Other comparisons with dsh-superagent (DeepSeek) 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.