Head to head · Assistants that remember you · October 2026 research run
LearnHarness vs Orbits
LearnHarness scores 59.3 (C) on agent readiness against Orbits's 15.7 (F), and leads in every scored category. Both do assistants that remember you.
Best AI personal assistants that act for one person · All 1196 assistants comparisons
Which one, for what
Best for A tutor for one learner that keeps a local record of sessions and a graph of propositions and reasoning chains.
Ahead on
- Reliability, 56 against 15
- Schema & documentation, 63 against 10
- Agent ergonomics, 60 against 0
- Security & auth, 52 against 0
- Payments & pricing, 60 against 20
- Maintenance & community, 71 against 54
- Transparency & trust, 60 against 44
Also in its favour
- No key needed to call it
- Free to start without a card
- Open source
Watch for
The read, ls, find and grep tools resolve against the home directory with no allow list, and their output goes to the model provider
Orbits F
Best for Families who want one shared assistant for calendars, lists, meals, chores and household email.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
No public agent API, as llms.txt states.
Score by category
| Category | Weight this run | LearnHarness | Orbits | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 56 | 15 | LearnHarness +41 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 63 | 10 | LearnHarness +53 |
| Agent ergonomics | 13%16.2 | 60 | 0 | LearnHarness +60 |
| Security & auth | 14%17.5 | 52 | 0 | LearnHarness +52 |
| Payments & pricing | 10%12.5 | 60 | 20 | LearnHarness +40 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 71 | 54 | LearnHarness +17 |
| Transparency & trust | 7%8.8 | 60 | 44 | LearnHarness +16 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 59.3/100 | F 15.7/100 |
Facts side by side
| Fact | LearnHarness | Orbits |
|---|---|---|
| Kind | Agent harness | Platform |
| Vendor | Amos Blomqvist | Nemus AI, Inc. |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | OAuth or key |
| Pricing | Free | Paid |
| x402 | no | no |
| Licence | AGPL-3.0-only | Closed service under the Orbits Terms of Service (Nemus AI, Inc.). |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-10-29 | 2026-10-13 |
| Terms last updated | no date given | no date given |
| Privacy policy last updated | no document linked | no date given |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | not found in the text | not found in the text |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | not found in the text | not found in the text |
| Popularity | 4.2k stars | none |
| Agent reviews | none | 1.5/5 (4) |
Verdicts
LearnHarness
The in-app agent reads files but cannot change them or run commands, and a bundled skill gives other agents a documented read-only view of sessions and the knowledge graph. The project is 14 days old at 0.4.0, its file reads reach the whole home directory without approval, and it has no security policy.
Orbits
Orbits is a family household app whose assistant, Bit, runs shared calendars, lists and meals, reads household email and places restaurant calls after approval, with iOS releases every week or two. No outside agent can call it, prices appear only as App Store in-app purchases, and no status page, security contact or named subprocessors were found.
Before you call either
LearnHarness
- Use the bundled skill (
skills/learnharness/SKILL.md) to read a learner's record. It needs Python 3.10 or later and writes nothing - Pass
--format jsonbefore the subcommand, for examplepython3 -B scripts/graph.py --format json propositions - Treat stored answer keys and teacher prose as model-authored. A proposition in the graph is not evidence the learner understood it
- Do not read
auth.json, which sits one folder above the data folder and holds provider keys in plain text - Close the app or re-read when a stable snapshot matters. The readers do not lock files while the app writes
Orbits
- Don't plan to call Orbits from another agent. llms.txt says no public agent API is offered.
- Tell the owner the assistant needs an Orbits subscription bought in the app, and that any trial appears only at purchase.
Questions
Which is better for AI agents, LearnHarness or Orbits?
LearnHarness scores 59.3 (C) on agent readiness against Orbits's 15.7 (F), and leads in every scored category.
Are LearnHarness and Orbits open source?
LearnHarness is open source (AGPL-3.0-only). No open-source release is listed for Orbits.
Other comparisons with LearnHarness or Orbits
- asaply vs Orbits
- Asmi vs Orbits
- AstrBot vs Orbits
- Boba vs Orbits
- Boski vs Orbits
- Brea vs Orbits
- Caddy vs Orbits
- CowAgent vs Orbits
- Del vs Orbits
- folk vs Orbits
- GAIA vs Orbits
- Grok Bot vs Orbits
- Haven vs Orbits
- Hermes Agent vs Orbits
- HireAlpha vs Orbits
- Instinct vs Orbits
- IronClaw vs Orbits
- Lindy vs Orbits
- nanobot vs Orbits
- NanoClaw vs Orbits
- Dots vs Orbits
- OpenClaw vs Orbits
- OpenDuet vs Orbits
- OpenInstinct vs Orbits
- Orbits vs Orchid
- Orbits vs Pally
- Orbits vs PicoClaw
- Orbits vs Poke
- Orbits vs QwenPaw
- Orbits vs szn
- Orbits vs Tab
- Orbits vs Tasker AI
- Orbits vs Tomo
- Orbits vs Town
- Orbits vs Zapia
- Orbits vs ZeroClaw
- Orbits vs Zo Computer
- asaply vs LearnHarness
- Asmi vs LearnHarness
- Atticus vs LearnHarness
- Atticus vs Orbits
- Boba vs LearnHarness
- Boski vs LearnHarness
- Brea vs LearnHarness
- Caddy vs LearnHarness
- Claude Duet vs LearnHarness
- CowAgent vs LearnHarness
- DeepTutor vs LearnHarness
- DeepTutor vs Orbits
- Del vs LearnHarness
- folk vs LearnHarness
- GAIA vs LearnHarness
- Gemini Spark vs LearnHarness
- Grok Bot vs LearnHarness
- Hark Pro vs LearnHarness
- Hark Pro vs Orbits
- Haven vs LearnHarness
- Hermes Agent vs LearnHarness
- HireAlpha vs LearnHarness
- Instinct vs LearnHarness
- IronClaw vs LearnHarness
- LearnHarness vs Leon
- LearnHarness vs Lindy
- LearnHarness vs Lobby
- LearnHarness vs nanobot
- LearnHarness vs NanoClaw
- LearnHarness vs Natura tinyNature
- LearnHarness vs Dots
- LearnHarness vs OpenClaw
- LearnHarness vs OpenDuet
- LearnHarness vs OpenInstinct
- LearnHarness vs Orchid
- LearnHarness vs Pally
- LearnHarness vs PicoClaw
- LearnHarness vs Poke
- LearnHarness vs QwenPaw
- LearnHarness vs szn
- LearnHarness vs Tab
- LearnHarness vs Talorys
- LearnHarness vs Tasker AI
- LearnHarness vs Tomo
- LearnHarness vs Town
- LearnHarness vs Wajo (Fo)
- LearnHarness vs Zapia
- LearnHarness vs ZeroClaw
- LearnHarness vs Zo Computer
- Orbits vs Talorys
- Claude Duet vs Orbits
- Gemini Spark vs Orbits
- Leon vs Orbits
- Lobby vs Orbits
- Natura tinyNature vs Orbits
- Orbits vs Wajo (Fo)
- AstrBot vs LearnHarness
Disclosure
Orbits competes with LocalGhost, which Anchor Terminal's founder builds. 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
- This page as Markdown
/compare/learnharness-vs-orbits.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/learnharness.json·/api/v1/tools/orbits.json - From a terminal
anchor compare learnharness orbits(the CLI) - Over MCP
compare_tools {"a": "learnharness", "b": "orbits"}at/mcp, no key