memory
ALWAYS ACTIVE — Selective persistent memory: preserve verified, durable knowledge worth reconstructing, with safe topic updates…
Persistent memory discipline for Engram contributors. Trigger: Decisions, bugfixes, discoveries, preferences, or session closure.
Claude Code
$ npx -y skills add Gentleman-Programming/engram --skill memory-protocol --agent claude-code
Codex
$ npx skills add Gentleman-Programming/engram --skill memory-protocol -a codex -y
Cursor
$ npx skills add Gentleman-Programming/engram --skill memory-protocol -a cursor -y
Gemini CLI
$ npx skills add Gentleman-Programming/engram --skill memory-protocol -a gemini-cli -y
GitHub Copilot
$ npx skills add Gentleman-Programming/engram --skill memory-protocol -a github-copilot -y
OpenCode
$ npx skills add Gentleman-Programming/engram --skill memory-protocol -a opencode -y
Windsurf
$ npx skills add Gentleman-Programming/engram --skill memory-protocol -a windsurf -y
name: engram-memory-protocol description: > Persistent memory discipline for Engram contributors. Trigger: Decisions, bugfixes, discoveries, preferences, or session closure. license: Apache-2.0 metadata: author: gentleman-programming version: "1.0"
The agent MUST follow this protocol without waiting for activation. Canonical prose lives in DOCS.md; this contributor skill is manually maintained.
Persist verified knowledge that is durable and costly to reconstruct: decisions with rationale, non-obvious root causes, real constraints, and resumption-relevant pending work. Group related conclusions deliberately, not every task, response, or event. Exclude secrets, private data, speculation, raw dumps, and routine progress.
Search when materially useful for recall or related work; mere project mentions do not require a search. For recall: mem_context, then mem_search with distinctive keywords, then mem_get_observation for full content. Narrow by project/type after broad recall as needed.
For selected writes, use mem_search on the bounded topic in the intended project and scope before writing. Read candidates in full with mem_get_observation; snippets are not identity evidence. For the same bounded topic use mem_update by ID: keep topic_key, preserve every still-valid fact, and record superseded facts as history. For a genuinely new topic use mem_save with a deliberate, distinct topic_key. If already covered, write nothing. On ambiguous identity or failed lookup, do not overwrite or fall back to a duplicate save. A failed read is not evidence of absence. A suggested topic_key is a hint, not proof of identity. Never merge across projects or scopes. Structure content as What, Why, Where, Learned.
At significant explicit closure or handoff, call mem_session_summary with Goal, Instructions, Discoveries, Accomplished, Next Steps, Relevant Files. Ordinary task completion does not require a summary. After relevant compaction, follow the host's recovery instructions; otherwise persist the compacted summary first, recover context, then continue. Summary persistence does not itself end a session; retain the host's attribution, registration, privacy, and lifecycle obligations.
Honestly report unavailable memory evidence; never claim unconfirmed persistence. Do not blindly repeat writes. Complete unrelated work even if bookkeeping fails. Do not add per-event learning sections or ceremonial delivery blocks.
---
Memory operations are internal bookkeeping, never the user-facing answer. Complete required memory work before composing the completed-task reply; send the complete answer as the final message of the turn with no later tool calls. If memory work fails or needs follow-up, still send the answer.
Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.
ALWAYS ACTIVE — Selective persistent memory: preserve verified, durable knowledge worth reconstructing, with safe topic updates…
Architecture guardrails for Engram across local store, cloud sync, dashboard, and plugins. Trigger: Any change that affects…
Backlog triage protocol for Engram: audit open issues and PRs, classify each item, infer maintainer ideology from comments, and…
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a…
Product and business-rule guardrails for Engram. Trigger: Any change that affects sync behavior, project controls, permissions,…
Commit and branch naming standards for Engram contributors, enforced by GitHub rulesets. Trigger: Any commit creation, review, or…
Believable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude…
Keep a durable record of work passed between Bots in the shared Hindsight memory bank. Use when handing work to another Bot, when…
Install, configure, and operate MemPalace, including a private local palace, a shared-brain hub, or a client joining an existing…
Install, configure, and operate MemPalace, including a private local palace, a shared-brain hub, or a client joining an existing…