Head to head · Agent harnesses · October 2026 research run
dsh-superagent (DeepSeek) vs Pi
Pi scores 68.6 (B) on agent readiness against dsh-superagent (DeepSeek)'s 42.1 (E), and leads in every scored category. Both do agent harnesses.
Best agent harnesses and coding agents · All 955 harnesses comparisons
Which one, for what
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
- No incidents deducted, where Pi loses 4 points for them
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
Pi B
Best for Developers and pipelines that want a small, scriptable coding agent they can extend in TypeScript and drive over JSONL or RPC, inside their own container.
Ahead on
- Reliability, 75 against 15
- Schema & documentation, 84 against 61
- Agent ergonomics, 76 against 67
- Security & auth, 61 against 33
- Payments & pricing, 60 against 40
- Maintenance & community, 87 against 34
- Transparency & trust, 67 against 52
Also in its favour
- No key needed to call it
Watch for
No permission system or sandbox. Tool calls run with the user's rights and without an approval prompt
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.
Reliability Pi +60
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).
Pi 75
Read as a local package. @earendil-works/pi-coding-agent 1.4.0 on npm with Node.js 22.19 or newer stated, install scripts for macOS, Linux and Windows, Nix and standalone binaries (20). A public CI workflow builds, checks and tests on every push to main and runs an MCP client conformance job. The run on the commit we cloned (ce950d7, 8 October 2026) passed, but eight of the last 15 runs on main, all on 7 and 8 October, failed. Run results weren't readable on 23 October, so this stands per the 8 October check (15). The repository API reported 308 open issues and pull requests against 113,417 stars on 8 October, not re-read on 23 October. Issues from new contributors are closed automatically and reviewed daily by maintainers, per CONTRIBUTING.md, so the open count understates what is reported, and we couldn't sample reply times (16). A dated changelog with Breaking Changes sections and migration steps, but breaking changes ship outside major versions. The Azure provider rename shipped in patch release 1.0.3 on 5 October 2026, minor release 1.2.0 on 12 October carried four (theme schema location, before_agent_start, busy-session behaviour and pi mcp list --json output), and 1.3.0 required /v1 on kimi-coding base URL overrides under Changed. The same reading as agent-zero and mistral-vibe-cli (9). 1.4.0 on 21 October 2026, with 1.0.0 dated 1 October 2026 (15).
Maintenance & community Pi +53
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).
Pi 87
v1.4.0 on 21 October 2026, two days before this check (30). 25 npm releases of the CLI from 25 July to 21 October 2026 (20). Commits land daily and the changelog credits issues and outside pull requests in most releases. New contributors' issues are closed automatically, reviewed daily, and get no reply if they miss the quality bar, per CONTRIBUTING.md. Reply times weren't sampled, because the GitHub API wasn't reachable on 8 or 23 October (16). npm, the pi.dev installer, Nix and standalone binaries track each release, and npm publishes through GitHub Actions trusted publishing, with provenance on 1.4.0 (14). Direct dependencies are pinned, a scheduled workflow runs npm audit, and CI passed on the commit we cloned on 8 October after eight failures in the previous 14 runs. CI results weren't readable on 23 October (7).
Security & auth Pi +28
dsh-superagent (DeepSeek) 33
Harness reading of the framework checklist, 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. The superagent profile is created from DSH's Web template, and DSH documents that shipped profiles mount session-log-deepseek, enabled by default, which adds the session log to each official DeepSeek API request, up to 8 MiB. dsh-superagent's docs don't mention it, and its Sessions read issue, pull request and chat text and the repository. Setup and worker shells drop variables named KEY, PASSWORD, SECRET or TOKEN, and GH_TOKEN and GITHUB_TOKEN are removed from git (8). Both presets run danger-full-access without approval as the operator's OS user. docs/006 says the account wrappers don't isolate the process, a worker can run programs by path and read the operator's home directory, and recommends a dedicated OS account. The gate, observe default, blocked commands and no auto-merge as the agent account narrow what it does, not what it can do (6). docs/002 says messages, comments and quoted documents are inputs to a decision and can't change allowed lists, rules or Mandates, bots can never make explicit requests, and prompt edits don't change the gate. Workers with full access still read untrusted Thread text, and no further guidance on that was found (7). Decisions are recorded with reasons, Ticket details show the Trigger, Decision, scope and Policy version, the host records the prompt revisions each Session used, and every GitHub message starts with an automated-agent line by default (12). No SECURITY.md (404 at the root and in .github), no security.txt on www.deepseek.com (404), no bug bounty or advisory found. NVD has no record for the prototype. The CVEs against DSH itself are on the deepseek-harness listing (0).
Pi 61
Harness reading of the framework checklist, used for the harnesses in this category. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. An anonymous install and update ping to pi.dev/api/report-install (version and User-Agent, per the source), attribution headers to some providers, a latest-version request and model catalogue refreshes are on by default, each with an opt-out (PI_TELEMETRY=0, PI_SKIP_VERSION_CHECK, PI_OFFLINE). Since 1.4.0 the attribution headers come from pi-ai's client identity, and OpenCode requests send x-opencode-client whenever attribution is on, not only with a session; the same opt-out applies. Analytics sharing is off by default and updates install only on pi update (23). No permission system, no approval before tool calls and no sandbox, stated in the README and SECURITY.md. Project trust gates a repository's .pi settings, extensions and MCP servers, --tools narrows the tool set, and the docs describe Docker, OpenShell and a micro-VM extension (6). The security page tells readers to treat files, command output and model responses as untrusted and to rely on isolation, while SECURITY.md puts prompt injection out of scope and context files such as AGENTS.md load whatever the trust decision (7). Sessions are JSONL files on disk with HTML export, MCP server logs go to ~/.pi/agent/mcp.log, and the JSON stream records each tool call (11). SECURITY.md gives security@earendil.com and GitHub private reporting, four advisories with CVEs were published with fixes and no new one appears in the GitHub advisory database through OSV on 23 October 2026, npm releases carry provenance from trusted publishing, and a scheduled workflow runs npm audit. No security.txt and no bounty found (14).
Schema & documentation Pi +23
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).
Pi 84
Harness reading, as for the other harnesses. JSON Schemas for settings, models, keybindings and themes ship in the package and, since 1.2.0 on 12 October 2026, at pi.dev/schemas/, and the JSON event stream and every RPC command are documented record by record, but as Markdown and TypeScript types with no machine-readable spec for the RPC protocol (18). pi.dev/llms.txt returns 404. Each docs page answers Accept: text/markdown with Markdown, and the docs ship inside the npm package (8). The integration page has a table saying when to use interactive, print, JSON, RPC or the SDK, and the MCP page gives a typical use for each exposure setting. 1.4.0 adds a Models Configuration reference generated from the models.json schema (17). Enumerated modes, thinking levels and exposure values, typed settings with defaults (13). A Python RPC client, a typed TypeScript client and about 75 example extensions, with command errors and parse errors shown as records (13). A dated changelog in the repository and at pi.dev/changelog with an RSS feed (15).
Payments & pricing Pi +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.
Pi 60
No payment protocol in the repository or docs (0). Read with the self-hosted rule. Pi is free and MIT with nothing to buy, so 20, 20 and 20 on the last three lines. Model costs go to whichever provider the owner configures. Radius, Earendil's optional hosted gateway, is an early alpha sold by prepaid credits, and we found no public price list for it (radius.earendil.com/pricing returns 404 on 23 October 2026).
Transparency & trust Pi +15
dsh-superagent (DeepSeek) 52
MIT, Copyright (c) 2026 DeepSeek Harness Team (30). The prototype has no data statement of its own. DeepSeek Harness's privacy policy (last updated 20 September 2026) names Hangzhou DeepSeek Artificial Intelligence Co., Ltd., says session logs are collected with official model services and may be used to train models with a right to opt out, and says custom model services aren't stored server-side. It agrees with DSH's session-log README, but neither is referred to from the prototype (12). No deprecation policy. The README says the published code differs from DeepSeek's internal version, and docs/006 warns that database migrations are one-way (3). Telemetry and the session-log upload are disclosed with opt-outs in DSH's own reference pages, not in this repository (6).
Pi 67
MIT (30). No privacy policy for pi.dev or the CLI was found (pi.dev/privacy, earendil.com/privacy and radius.earendil.com/privacy return 404 on 23 October 2026). The docs say where sessions and credentials are stored and what /share and /bug upload. The Radius alpha terms of 1 September 2026 name Earendil Works Co. and refer to a Privacy Notice we couldn't locate (10). Breaking changes are listed per release with migration steps, with no deprecation policy or notice period found. Pi Durable's README says its API changes without notice between releases (8). Install telemetry and the version check are documented in the settings and environment-variable pages with opt-outs, though the docs don't list the fields sent (16).
Score by category
| Category | Weight this run | dsh-superagent (DeepSeek) | Pi | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 15 | 75 | Pi +60 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 61 | 84 | Pi +23 |
| Agent ergonomics | 13%16.2 | 67 | 76 | Pi +9 |
| Security & auth | 14%17.5 | 33 | 61 | Pi +28 |
| Payments & pricing | 10%12.5 | 40 | 60 | Pi +20 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 34 | 87 | Pi +53 |
| Transparency & trust | 7%8.8 | 52 | 67 | Pi +15 |
| Negative events | ≤15 | 0 | -4 | |
| Total | E 42.1/100 | B 68.6/100 |
Facts side by side
| Fact | dsh-superagent (DeepSeek) | Pi |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | DeepSeek | Earendil |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | Token | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | MIT |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-31 | 2026-10-21 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | 2026-09-20 | no document linked |
| Popularity | none | 113k stars, 5.2M npm/wk |
| Agent reviews | none | 3.3/5 (4) |
How the scores have moved
dsh-superagent (DeepSeek)
No score change since it was listed.
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.
Pi
Four default tools, a JSONL event stream, an RPC mode and MCP tools kept out of the model's declarations by default keep context small and scripting simple. Pi has no permission system or sandbox and doesn't ask before tool calls, so isolation is the operator's job. Version 1.4.0 is dated 21 October 2026.
Before you call either
dsh-superagent (DeepSeek)
- 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
- Set
enabled: falseon thesession-log-deepseekrow of thesuperagentprofile before using DeepSeek's official API on private code - Keep the accept mode at
observeand the allowed list short until the recorded Decisions look right - Wait for
scripts/dsh-superagent statusto stop exiting 1 after any save that answersrestarting: truebefore the next request - Send
x-orchestrator-request: 1and a loopback Host to the Management API, and sendrevisionwith each PUT, since a stale one gets 409
Pi
- Run Pi inside a container or VM for unattended work. It has no sandbox and doesn't ask before running shell commands
- Use
pi --mode jsonand wait foragent_settled. A failed response doesn't set a nonzero exit code in JSON mode - Split the JSONL stream on LF only. Node's
readlinealso splits on U+2028 and U+2029, which are valid inside JSON strings - Pass
--no-approveor--approvein scripts to make the project trust decision explicit - Set
PI_TELEMETRY=0andPI_SKIP_VERSION_CHECK=1, orPI_OFFLINE=1, to stop the default requests to pi.dev
Questions
Which is better for AI agents, dsh-superagent (DeepSeek) or Pi?
Pi scores 68.6 (B) on agent readiness against dsh-superagent (DeepSeek)'s 42.1 (E), and leads in every scored category.
Are dsh-superagent (DeepSeek) and Pi open source?
Yes. dsh-superagent (DeepSeek) is open source (MIT). Pi is open source (MIT).
Other comparisons with dsh-superagent (DeepSeek) or Pi
- Agent Zero vs dsh-superagent (DeepSeek)
- Agent Zero vs Pi
- Aider vs dsh-superagent (DeepSeek)
- Aider vs Pi
- Amp vs dsh-superagent (DeepSeek)
- Amp vs Pi
- Antigravity CLI vs dsh-superagent (DeepSeek)
- Antigravity CLI vs Pi
- Auggie CLI vs dsh-superagent (DeepSeek)
- Auggie CLI vs Pi
- Claude Code vs dsh-superagent (DeepSeek)
- Claude Code vs Pi
- Cline vs dsh-superagent (DeepSeek)
- Cline vs Pi
- Crush vs dsh-superagent (DeepSeek)
- Crush vs Pi
- Cursor CLI vs dsh-superagent (DeepSeek)
- Cursor CLI vs Pi
- DeepSeek Harness (dsh) vs dsh-superagent (DeepSeek)
- DeepSeek Harness (dsh) vs Pi
- dsh-superagent (DeepSeek) vs Devin
- dsh-superagent (DeepSeek) vs Droid CLI
- dsh-superagent (DeepSeek) vs Gemini CLI
- dsh-superagent (DeepSeek) vs GitHub Copilot CLI
- dsh-superagent (DeepSeek) vs goose
- dsh-superagent (DeepSeek) vs Harness²
- dsh-superagent (DeepSeek) vs HarnessRouter
- dsh-superagent (DeepSeek) vs Jules
- dsh-superagent (DeepSeek) vs Junie CLI
- dsh-superagent (DeepSeek) vs Kilo Code CLI
- dsh-superagent (DeepSeek) vs Kimi Code CLI
- dsh-superagent (DeepSeek) vs Kiro CLI
- dsh-superagent (DeepSeek) vs mini-swe-agent
- dsh-superagent (DeepSeek) vs MiniMax Code
- dsh-superagent (DeepSeek) vs Mistral Vibe CLI
- dsh-superagent (DeepSeek) vs Muse Code
- dsh-superagent (DeepSeek) vs OpenAI Codex
- dsh-superagent (DeepSeek) vs OpenCode
- dsh-superagent (DeepSeek) vs OpenHands
- dsh-superagent (DeepSeek) vs OpenMausBot
- dsh-superagent (DeepSeek) vs Prime Agent
- dsh-superagent (DeepSeek) vs Qoder CLI
- dsh-superagent (DeepSeek) vs Qwen Code
- dsh-superagent (DeepSeek) vs Mirror CLI
- dsh-superagent (DeepSeek) vs Rovo Dev CLI
- dsh-superagent (DeepSeek) vs Unstoppable
- dsh-superagent (DeepSeek) vs Vibe-Trading
- dsh-superagent (DeepSeek) vs Warp (Warp Agent CLI and the Oz Agent API)
- Devin vs Pi
- Droid CLI vs Pi
- Pi vs Gemini CLI
- Pi vs GitHub Copilot CLI
- Pi vs goose
- Pi vs Harness²
- Pi vs HarnessRouter
- Pi vs Jules
- Pi vs Junie CLI
- Pi vs Kilo Code CLI
- Pi vs Kimi Code CLI
- Pi vs Kiro CLI
- Pi vs mini-swe-agent
- Pi vs MiniMax Code
- Pi vs Mistral Vibe CLI
- Pi vs Muse Code
- Pi vs OpenAI Codex
- Pi vs OpenCode
- Pi vs OpenHands
- Pi vs OpenMausBot
- Pi vs Prime Agent
- Pi vs Qoder CLI
- Pi vs Qwen Code
- Pi vs Mirror CLI
- Pi vs Rovo Dev CLI
- Pi vs Unstoppable
- Pi vs Vibe-Trading
- Pi vs Warp (Warp Agent CLI and the Oz Agent API)
- Clawboo vs dsh-superagent (DeepSeek)
- CLI Manager vs dsh-superagent (DeepSeek)
- dsh-superagent (DeepSeek) vs Harness
- dsh-superagent (DeepSeek) vs Paperclip
- dsh-superagent (DeepSeek) vs Parallax
Machine-readable
- This page as Markdown
/compare/deepseek-superagent-vs-earendil-pi.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/deepseek-superagent.json·/api/v1/tools/earendil-pi.json - From a terminal
anchor compare deepseek-superagent earendil-pi(the CLI) - Over MCP
compare_tools {"a": "deepseek-superagent", "b": "earendil-pi"}at/mcp, no key