Skip to content
Agentmart
Submit a tool

dream

Consolidate mem0 — merge duplicates, resolve contradictions, prune clearly-stale entries.

Skill by pjope

IndexedMIT
Write a review

Chalk Labs

Need help deploying dream?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/pjope-dream

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Consolidate mem0 — merge duplicates, resolve contradictions, prune clearly-stale entries. Shows a diff and asks before changing anything unless run with --auto. Use when the store has grown noisy.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/dream

What's inside

Skill name
dream
Description
Consolidate mem0 — merge duplicates, resolve contradictions, prune clearly-stale entries. Shows a diff and asks before changing anything unless run with --auto. Use when the store has grown noisy.
License
MIT
Instructions
30 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Dream

A consolidation pass. It mutates memory, so the default is propose-then-confirm; `--auto` applies only the safe merges without asking.

Read the curated set with `get_memories` using `exclude_sources: ["session", "archived"]` and `limit` 1000 — raw captures are never consolidation targets (distillation owns their lifecycle).

**Completeness gate — check before anything else.** Compare the returned count against the response's `total_matching`. If fewer memories came back than matched — or the response has no `total_matching` field at all (server predates the filter patch) — you are looking at a partial, arbitrarily-sampled view. **Propose nothing destructive from a partial view**: a "duplicate" whose twin is outside the window isn't a duplicate, and a "contradiction" may already be resolved by an unseen entry. Report the truncation, suggest raising the limit, and stop.

With the full set in hand, work out a plan in three buckets:

**Merge** — groups of near-duplicates. Pick the clearest wording (or compose one that covers the group), and plan to replace the group with it.

**Resolve** — contradictory pairs. The newer `created_at` usually wins, but if it's ambiguous, ask rather than guess.

**Prune** — only entries that are clearly dead: superseded by a merge, or pointing at a tool/path the repo no longer has. When unsure, keep it.

Show the plan as a diff before touching anything:

```
## dream — 412 of 412 curated memories scanned
merge 3 → 1: "deploys via CI" (drops [mem0:a1],[mem0:b2],[mem0:c3])
resolve: keep [mem0:d4] (2026-06), drop [mem0:e5] (2026-01)
prune: [mem0:f6] — references the old Traefik route
```

On approval, apply each: a merge is `add_memory` of the kept text (`infer=false`, carry the type) followed by `delete_memory` on the originals; a resolve/prune is `delete_memory`. There's no rollback, so finish only after the writes succeed and report the net change.

`--auto` runs merges of obvious duplicates silently and leaves contradictions and prunes for a human. The completeness gate applies to `--auto` too — a truncated fetch means no automatic changes at all.

From pjope/mem0-selfhosted-hooks, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 7, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from pjope

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get dream running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying dream?

CallGet help
Cite this page

dream skill. Agent Mart. https://agentmart.dev/skills/pjope-dream (last updated 2026-10-24)