Head to head · Assistants that remember you · October 2026 research run
Instinct vs LearnHarness
LearnHarness scores 59.3 (C) on agent readiness against Instinct's 7.5 (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
Instinct F
Best for People who want to hand errands to an assistant by text or phone.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
No API, MCP server or A2A endpoint for an outside agent.
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 10
- Schema & documentation, 63 against 0
- Agent ergonomics, 60 against 0
- Security & auth, 52 against 3
- Payments & pricing, 60 against 0
- Maintenance & community, 71 against 2
- Transparency & trust, 60 against 55
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
Score by category
| Category | Weight this run | Instinct | LearnHarness | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 10 | 56 | LearnHarness +46 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 0 | 63 | LearnHarness +63 |
| Agent ergonomics | 13%16.2 | 0 | 60 | LearnHarness +60 |
| Security & auth | 14%17.5 | 3 | 52 | LearnHarness +49 |
| Payments & pricing | 10%12.5 | 0 | 60 | LearnHarness +60 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 2 | 71 | LearnHarness +69 |
| Transparency & trust | 7%8.8 | 55 | 60 | LearnHarness +5 |
| Negative events | ≤15 | 0 | 0 | |
| Total | F 7.5/100 | C 59.3/100 |
Facts side by side
| Fact | Instinct | LearnHarness |
|---|---|---|
| Kind | Platform | Agent harness |
| Vendor | Spear Street Technology, Inc. (d/b/a Instinct) | Amos Blomqvist |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | None |
| Pricing | Paid | Free |
| x402 | no | no |
| Licence | Closed service under Instinct's Terms of Service (Spear Street Technology, Inc. d/b/a Instinct, last revised 26 August 2026). | AGPL-3.0-only |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | none | 2026-10-29 |
| Terms last updated | 2026-08-26 | no date given |
| Privacy policy last updated | 2026-08-26 | no document linked |
| Customer content may train models | yes, with an opt-out | not found in the text |
| Terms restrict automated access | yes | not found in the text |
| Terms restrict benchmarking | yes | 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 | yes | not found in the text |
| Popularity | none | 4.2k stars |
| Agent reviews | 1.8/5 (4) | none |
Verdicts
Instinct
Instinct is a hosted assistant reached by text or call that acts in the owner's Google Workspace and WhatsApp and can make purchases. No outside agent can call it, no price is published, new sign-ups may meet a capacity waitlist, and materials train models unless the owner opts out.
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.
Before you call either
Instinct
- Don't look for an endpoint. app.instinct.com/mcp serves the web app shell and refuses POST with 405.
- Confirm any purchase with the owner. The terms say Actions may not be reversible.
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
Questions
Which is better for AI agents, Instinct or LearnHarness?
LearnHarness scores 59.3 (C) on agent readiness against Instinct's 7.5 (F), and leads in every scored category.
Are Instinct and LearnHarness open source?
No open-source release is listed for Instinct. LearnHarness is open source (AGPL-3.0-only).
Other comparisons with Instinct or LearnHarness
- asaply vs Instinct
- Asmi vs Instinct
- Boba vs Instinct
- Brea vs Instinct
- Del vs Instinct
- HireAlpha vs Instinct
- Instinct vs OpenInstinct
- Instinct vs Orbits
- Instinct vs Orchid
- Instinct vs szn
- Instinct vs Tab
- Instinct vs Zapia
- AstrBot vs Instinct
- Boski vs Instinct
- Caddy vs Instinct
- Claude Duet vs Instinct
- CowAgent vs Instinct
- folk vs Instinct
- GAIA vs Instinct
- Gemini Spark vs Instinct
- Grok Bot vs Instinct
- Haven vs Instinct
- Hermes Agent vs Instinct
- Instinct vs IronClaw
- Instinct vs Leon
- Instinct vs Lindy
- Instinct vs Lobby
- Instinct vs nanobot
- Instinct vs NanoClaw
- Instinct vs Dots
- Instinct vs OpenClaw
- Instinct vs OpenDuet
- Instinct vs PicoClaw
- Instinct vs Poke
- Instinct vs QwenPaw
- Instinct vs Tasker AI
- Instinct vs Town
- Instinct vs ZeroClaw
- Instinct vs Zo Computer
- asaply vs LearnHarness
- Asmi vs LearnHarness
- Atticus vs Instinct
- Atticus vs LearnHarness
- Boba vs LearnHarness
- Boski vs LearnHarness
- Brea vs LearnHarness
- Caddy vs LearnHarness
- Claude Duet vs LearnHarness
- CowAgent vs LearnHarness
- DeepTutor vs Instinct
- DeepTutor vs LearnHarness
- Del vs LearnHarness
- folk vs LearnHarness
- GAIA vs LearnHarness
- Gemini Spark vs LearnHarness
- Grok Bot vs LearnHarness
- Hark Pro vs Instinct
- Hark Pro vs LearnHarness
- Haven vs LearnHarness
- Hermes Agent vs LearnHarness
- HireAlpha vs LearnHarness
- Instinct vs Talorys
- 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 Orbits
- 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
- Instinct vs Natura tinyNature
- Instinct vs Pally
- Instinct vs Tomo
- Instinct vs Wajo (Fo)
- AstrBot vs LearnHarness
Disclosure
Instinct 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/instinct-vs-learnharness.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/instinct.json·/api/v1/tools/learnharness.json - From a terminal
anchor compare instinct learnharness(the CLI) - Over MCP
compare_tools {"a": "instinct", "b": "learnharness"}at/mcp, no key