Pimp My IDE / Garage Dispatch
← Back to garage
September 17, 2026 · local search / portable sessions / useful memory

Your agent does not need one big memory.

It needs a salvage yard: separate racks for things you read, turns you ran, corrections you earned, and authority you are willing to grant. “Remember everything” is not a feature. It is an unsorted warehouse with a forklift key under the mat.

THE TAKE: Corpus recall, session continuity, durable correction, and action authority are different systems. Index them differently. Expire them differently. Never let “the agent found it” quietly become “the agent may act on it.”
Sort the context salvage yard ↓

Personal search just drove into the agent bay.

Hister describes itself as a private search engine for pages you visit and files you keep. It indexes full contents, can ingest browser history and local directories, and exposes search through a web interface, terminal clients, and MCP. Its default posture is local or self-hosted with no telemetry or mandatory cloud service; optional semantic search can send document text to an embeddings endpoint chosen by the operator.[1]

That is useful because most context failure is not mystical. You saw the exact caveat three Tuesdays ago, buried in a release note, and now neither you nor the model can find it. Full-text recall turns “I vaguely remember” into a retrievable object.

A searchable pile is memory for finding. It is not memory for steering.

A transcript is cargo, not judgment.

Skillsync’s launch post makes a different move: translate agent sessions across incompatible on-disk formats. The authors say the system can carry messages, reasoning, and tool history between coding agents, while storing skills and memory as portable human-readable Markdown; session translation is local unless a user explicitly shares into a team workspace.[2]

VS Code 1.138 attacks continuity from inside the editor. Its Agent Host can keep the same session available across windows; the release also says Codex sessions can continue across apps, quick chats can attach to a folder or isolated worktree, and local sessions can run inside a Dev Container. Those are placement and continuity features—not proof that stale assumptions, permissions, or failed experiments should survive the move.[3]

A transcript tells the next driver what happened. It does not tell them which statement was later disproved, which tool output was environment-specific, or which permission should be revoked at the handoff.

Corrections need promotion, not accumulation.

Detail’s argument for “self-driving codebases” names global memory as a missing primitive: if one agent learns that an audit table is append-only, future agents touching that area should not need the same correction repeated. The post also argues that agent blind spots in development environments limit trust and that traces from bug-fixing work should expose which environment gaps deserve investment.[4]

The important word is not global. It is correction. A durable rule should be promoted because evidence changed the team’s operating model—not because a sentence happened to occur in a long chat. The promotion path needs provenance, scope, an owner, and an invalidation condition.

Build four racks, then put a gate between recall and action.

Corpus rack: pages, files, docs, release notes, and search indexes. Attach source, capture date, sensitivity, and retention. Session rack: prompts, tool calls, outputs, workspace identity, model or harness, and handoff summary. Preserve sequence without pretending every turn remains true.

Correction rack: reviewed lessons promoted into repository instructions, tests, runbooks, or policy—with an owner and expiry trigger. Authority rack: current credentials, tool grants, write targets, network reach, spend ceilings, and human brakes. This rack is checked live; it is not inherited from prose.

The salvage control below replaces a single “memory on” switch with four native intake gates. It executes no search and grants no permissions. Closing all four gates means the review template is ready to fill; the gauge measures declared sorting coverage, not truth, freshness, or safety.

Interactive makeover / physical sorting crane

Context Salvage Yard.

Traditional purpose replaced: one “remember everything” toggle. Better version: four native gates separate searchable material, portable history, promoted corrections, and live authority into a copyable intake card.

Sort before you lift

The crane is a teaching readout. It mirrors declared intake coverage, not memory quality or access safety.

Context salvage intake gates

Salvage intake card

0/4 gates closed · TEMPLATE INCOMPLETE. Nothing has been sorted, verified, or authorized.

Open the four-source evidence drawer
[1] Hister README — full-content indexing for visited pages and local files; browser, terminal, and MCP clients; default local/self-hosted privacy posture; optional embeddings boundary. [2] Skillsync Launch HN, September 17, 2026 — authors’ description of local session translation, cross-agent portability, human-readable skills/memory, search, and explicit team sharing. [3] Visual Studio Code 1.138 release notes, September 16, 2026 — Agent Host continuity, cross-app Codex sessions, workspace/worktree attachment, and local Dev Container placement. [4] Detail, “Towards Self-Driving Codebases,” September 2, 2026 — opinionated thesis on global memory, environment blind spots, correction reuse, and agent-ready dev stacks.

Source boundary: Hister and Skillsync feature statements are project-author claims. VS Code notes include preview and gradual-rollout behavior. Detail’s piece is an argument from a vendor, not neutral benchmark evidence. The four-rack model and all copyable fields are Pimp My IDE editorial guidance.