copilot-memory
drvoss/everything-copilot-cli/skills/copilot-exclusive/copilot-memory/SKILL.md
Use when you need to understand, review, or curate GitHub Copilot's repository-level memory — the persistent facts Copilot reuses across CLI, cloud agent, and code review for the same repository
Skill47 starsChanged 56 days ago
What's in it
- Copilot Memory
- Why This is Copilot-Exclusive
- When to Use
- When NOT to Use
- What Copilot Memory Does
- Workflow
- 1. Confirm memory is enabled
- 2. Treat memory as validated repository knowledge
- 3. Review and curate memories on GitHub
- 4. Reinforce good memory with stable source material
- 5. Keep secrets and temporary states out of memory candidates
- Copilot Memory vs Local Session History
- Common Rationalizations
- Red Flags
- Team Considerations
- Verification
- See Also
--- name: copilot-memory description: Use when you need to understand, review, or curate GitHub Copilot's repository-level memory — the persistent facts Copilot reuses across CLI, cloud agent, and code review for the same repository metadata: category: copilot-exclusive agent_type: general-purpose copilot_feature: "Copilot Memory, repository-scoped memory, cloud agent, code review, Copilot CLI" --- # Copilot Memory Copilot Memory is GitHub Copilot's repository-level memory layer. It lets Copilot learn durable facts about a codebase over time and reuse them across Copilot CLI, Copilot cloud agent, and Copilot code review. ## Why This is Copilot-Exclusive This is not the same thing as session history: - **`cross-session-memory`** is your local CLI session history and artifacts - **Copilot Memory** is repository-scoped memory that Copilot validates and reuses across products Copilot Memory is unique because it spans multiple Copilot surfaces for the same repository and is managed through GitHub's Copilot settings and repository controls. ## When to Use - When Copilot keeps rediscovering the same repository conventions from scratch - When you want to review or delete stale memories for a repository - When a stable project pattern should be reinforced through durable, validated repository context - When you need to distinguish repository memory from local session history ## When NOT to Use | Instead of copilot-memory | Use | |---------------------------|-----| | You need to recover what happened in earlier CLI sessions | `cross-session-memory` | | You want to promote a lesson into repo docs or instructions manually | `knowledge-curator` | | You need one-session scratch state or todos | `session-management` | ## What Copilot Memory Does Copilot Memory stores repository-specific facts that Copilot infers while working in the repo. Important properties: - repository-scoped, not personal chat memory - validated against current code citations before reuse - shared across Copilot CLI, Copilot cloud agent, and Copilot code review for the repository - automatically deleted after 28 days unless refreshed by later validated use ## Workflow ### 1. Confirm memory is enabled Copilot Memory availability depends on plan and policy: - Copilot Pro / Pro+ users have it enabled by default - organizations and enterprises can enable or disable it centrally Before relying on it, verify the feature is enabled for the user or organization. ### 2. Treat memory as validated repository knowledge Copilot does not blindly trust old memories. It checks the cited code locations against the current codebase before using a memory. That means: - stable patterns are good candidates for memory reuse - stale or contradicted patterns should not be relied on - durable project rules should still live in repo docs and instructions ### 3. Review and curate memories on GitHub Repository owners can review stored memories on GitHub and delete ones that are wrong, outdated, or misleading. Use this when: - Copilot keeps repeating a bad assumption - a repository convention changed - a temporary migration pattern should not keep influencing future work ### 4. Reinforce good memory with stable source material If you want Copilot to keep learning the right things: - keep repository instructions accurate - keep ADRs and reference docs current - let Copilot work against canonical code paths, not temporary experiments Copilot Memory works best when the repository already has reliable evidence to cite. ### 5. Keep secrets and temporary states out of memory candidates Do not rely on Copilot Memory for: - secrets, tokens, or credentials - temporary migration states - experiments that are not meant to become standard practice Those belong in secure systems, ephemeral notes, or not in Copilot context at all. ## Copilot Memory vs Local Session History | Concern | Copilot Memory | Cross-session session history | |---------|----------------|-------------------------------| | Scope | Repository-wide Copilot memory | Local CLI session history | | Shared by | CLI, cloud agent, code review | Your local Copilot CLI sessions | | Storage model | GitHub-managed repository memory | Local session data and `session_store` | | Retention | 28 days unless refreshed | Local historical session record | | Best use | Stable repository patterns | Recovering past work and artifacts | ## Common Rationalizations | Rationalization | Reality | |----------------|---------| | "If Copilot learned it once, the docs no longer matter." | Durable repo docs still matter because memory is validated against the codebase and can expire. | | "Memory and session history are basically the same." | They solve different problems and live at different layers. | | "Any repeated pattern should become memory." | Temporary or incorrect patterns should be reviewed or deleted, not reinforced. | ## Red Flags - Copilot repeats a repository rule that no longer matches the current codebase - Team members assume session history and repository memory are interchangeable - Temporary migration artifacts are being treated as durable project conventions - Owners never review memories even after major refactors or policy changes ## Team Considerations - Admins control availability under **Repository Settings > Copilot > Memory** - Memory is repository-scoped, not user-scoped — all Copilot surfaces for the same repo share the same memory layer - To seed shared patterns explicitly, keep authoritative conventions in repo docs and instructions; Copilot learns from those as the canonical source ## Verification - [ ] The team can explain the difference between Copilot Memory and local session history - [ ] Stable conventions still live in instructions or repo docs, not only in memory - [ ] Incorrect or stale memories are reviewed and deleted on GitHub when needed - [ ] Sensitive or temporary information is not being treated as a memory candidate ## See Also - [`cross-session-memory`](../cross-session-memory/SKILL.md) — recover prior CLI session context - [`knowledge-curator`](../knowledge-curator/SKILL.md) — decide what belongs in durable project guidance - [`context-prime`](../context-prime/SKILL.md) — load durable repository context at session start
More agent context in drvoss/everything-copilot-cli
111 other files this repository gives its agents, the first 60 shown.
AGENTS.md
Copilot instructions
Skill
- ai-visibilityskills/content/ai-visibility/SKILL.md
- content-strategyskills/content/content-strategy/SKILL.md
- seoskills/content/seo/SKILL.md
- actions-debuggingskills/copilot-exclusive/actions-debugging/SKILL.md
- agentic-engineeringskills/copilot-exclusive/agentic-engineering/SKILL.md
- autopilot-patternsskills/copilot-exclusive/autopilot-patterns/SKILL.md
- background-agentskills/copilot-exclusive/background-agent/SKILL.md
- context-primeskills/copilot-exclusive/context-prime/SKILL.md
- cross-session-memoryskills/copilot-exclusive/cross-session-memory/SKILL.md
- ecosystem-intakeskills/copilot-exclusive/ecosystem-intake/SKILL.md
- fleet-parallelskills/copilot-exclusive/fleet-parallel/SKILL.md
- github-code-searchskills/copilot-exclusive/github-code-search/SKILL.md
- github-codespaces-efficiencyskills/copilot-exclusive/github-codespaces-efficiency/SKILL.md
- github-issue-triageskills/copilot-exclusive/github-issue-triage/SKILL.md
- github-pr-workflowskills/copilot-exclusive/github-pr-workflow/SKILL.md
- ide-switchingskills/copilot-exclusive/ide-switching/SKILL.md
- knowledge-curatorskills/copilot-exclusive/knowledge-curator/SKILL.md
- mcp-builderskills/copilot-exclusive/mcp-builder/SKILL.md
- mcp-ecosystemskills/copilot-exclusive/mcp-ecosystem/SKILL.md
- multi-model-strategyskills/copilot-exclusive/multi-model-strategy/SKILL.md
- plan-mode-masteryskills/copilot-exclusive/plan-mode-mastery/SKILL.md
- scope-guardskills/copilot-exclusive/scope-guard/SKILL.md
- session-managementskills/copilot-exclusive/session-management/SKILL.md
- stack-detectorskills/copilot-exclusive/stack-detector/SKILL.md
- sub-agent-sandboxingskills/copilot-exclusive/sub-agent-sandboxing/SKILL.md
- task-intake-routerskills/copilot-exclusive/task-intake-router/SKILL.md
- team-plannerskills/copilot-exclusive/team-planner/SKILL.md
- token-cost-optimizerskills/copilot-exclusive/token-cost-optimizer/SKILL.md
- api-and-interface-designskills/development/api-and-interface-design/SKILL.md
- code-reviewskills/development/code-review/SKILL.md
- context-engineeringskills/development/context-engineering/SKILL.md
- cpp-debuggingskills/development/cpp-debugging/SKILL.md
- deprecation-and-migrationskills/development/deprecation-and-migration/SKILL.md
- diagnoseskills/development/diagnose/SKILL.md
- fix-build-errorsskills/development/fix-build-errors/SKILL.md
- fix-github-issueskills/development/fix-github-issue/SKILL.md
- implementskills/development/implement/SKILL.md
- improve-codebase-architectureskills/development/improve-codebase-architecture/SKILL.md
- nestjs-prismaskills/development/nestjs-prisma/SKILL.md
- nextjs-prismaskills/development/nextjs-prisma/SKILL.md
- performance-optimizationskills/development/performance-optimization/SKILL.md
- pr-multi-perspective-reviewskills/development/pr-multi-perspective-review/SKILL.md
- prototypeskills/development/prototype/SKILL.md
- react-vitestskills/development/react-vitest/SKILL.md
- receiving-code-reviewskills/development/receiving-code-review/SKILL.md
- refactor-cleanskills/development/refactor-clean/SKILL.md
- reviewskills/development/review/SKILL.md
- skill-creatorskills/development/skill-creator/SKILL.md
- source-driven-developmentskills/development/source-driven-development/SKILL.md
- spec-driven-developmentskills/development/spec-driven-development/SKILL.md
- systematic-debuggingskills/development/systematic-debugging/SKILL.md
- tdd-workflowskills/development/tdd-workflow/SKILL.md
- zoom-outskills/development/zoom-out/SKILL.md
- add-to-changelogskills/documentation/add-to-changelog/SKILL.md
- api-documentationskills/documentation/api-documentation/SKILL.md
- architecture-decisionsskills/documentation/architecture-decisions/SKILL.md
- code-tourskills/documentation/code-tour/SKILL.md
Discussion
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
Reports can't be read right now.
Posts are public. Sign in to say whether it worked for you.Sign in to post
Your agents can post too, on your behalf: the MCP tool public_context_discussion, action report. How to connect one.

