Skip to content

DeepTutor

v1.4.8 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai-agents ai-tutor clawdbot cli-tool deepresearch interactive-learning
+3 more
large-language-models multi-agent-systems llm

Summary

AI summary

Updates What's New, Upgrade Notes, and ver1-4-7.md across a mixed release.

Full changelog

DeepTutor v1.4.8 Release Notes

Release Date: 2026.06.18

A focused follow-up to v1.4.7: the agents you connect under
My Agents now include your own Partners, and every Partner gains a
private memory of its own. Connect a partner beside your local Claude Code /
Codex, select it in chat, and DeepTutor consults it live — its persona, library
and skills answering through the partner's own loop. Drop-in — no migrations.

A partner's memory now lives with the partner. Previously a partner read
and wrote the owner's shared memory; now each partner keeps its own
long-term memory in its workspace, while still reading the owner's shared
memory as context. This is non-destructive — the owner's memory is untouched
and stays readable — it only changes where a partner's new memories land.
Nothing to do on upgrade.

What's New

Consult a Partner as a Connected Agent

My Agents now lists your Partners next to a local Claude Code / Codex.
Connect one and select it in the composer, and the turn runs on a single
consult_subagent tool against that partner's own chat loop — its soul, library
and skills — streaming its trace live in the sidebar. Every consult within one
DeepTutor chat threads into a single partner session, archived in that partner's
history and titled from your first question, and the connection wears the
partner's own avatar.

Partners Get Their Own Memory

A partner now has a split memory model, exposed through three always-on
tools that replace chat's read_memory / write_memory on every partner turn:

  • partner_read — reads the owner's shared memory and the partner's own,
    concatenated.
  • partner_memorize — writes only to the partner's own workspace; a partner can
    never touch the owner's memory.
  • partner_search — keyword search over the partner's own conversation history.

Because these are mandatory, the per-Partner read_memory / write_memory
toggles are gone from Partner tool settings.

Reference a Partner Conversation as Context

A partner conversation can now be pulled into a DeepTutor chat as a referenced
transcript (admin-only), framed as a third party under the partner's own name —
the same way imported agent histories are.

Upgrade Notes

  • Drop-in from v1.4.7: pip install -U deeptutor; Docker users pull
    ghcr.io/hkuds/deeptutor:latest. No migrations.
  • The partner-memory change above is automatic and non-destructive: existing
    partners keep reading the owner's shared memory and simply gain their own
    writable store.

Full Changelog: https://github.com/HKUDS/DeepTutor/compare/v1.4.7...v1.4.8

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track DeepTutor

Get notified when new releases ship.

Sign up free

About DeepTutor

"DeepTutor: Agent-Native Personalized Learning Assistant"

All releases →

Related context

Earlier breaking changes

  • v1.4.5 Guided Learning rebuilt as tutor chat with hard mastery gate; old fixed-stage flow removed.
  • v1.4.0-beta Deletes the legacy main.yaml capability copy; each capability now uses its own prompt files
  • v1.4.0-beta Removes legacy main.yaml capability copy in favor of per-capability prompt files
  • v1.4.0-beta Removes legacy agents/ and prompts/ directories for research, solve, question modes

Beta — feedback welcome: [email protected]