eve / eve-memory-agent-template
AGENTS.md5.9k starsChanged 2 days agoApache-2.0View on GitHub
This repository is a reusable Slack-based assistant built on eve that saves the preferences people share with it. User preferences and channel conventions are stored in separate memory slots and recalled before the agent responds to each message. Use Node.js 24 and pnpm. These instructions are for agents maintaining the repository. The assistant's behavior is defined in agent/instructions.md and the dynamic instructions under agent/instructions/. Keep the template focused on memory. Features such as Slack tables, charts, or approval cards belong…
- Reads credentials
Trending
More talk lately.about the whole repository
Who's talking about vercel/eve
- @qdrddr.bsky.social“@vercel.com Eve #Agentic #framework uses #filesystem as interface for tools, just drop a #TypeScript code …”Bluesky · Oct 16, 2026 · 8 likes
- @projectnothing.bsky.social“When frameworks like eve break out, it’s a sign: AI agents are no longer side projects—they’re becoming a …”Bluesky · Jun 17, 2026 · 3 likes
- @github-trending-js.bsky.social“📦 vercel / eve ⭐ 5,184 (+40) 🗒 TypeScript The Open Framework for Building Agents”Bluesky · Sep 17, 2026 · 2 likes
- DataDog/dd-trace-js“feat(llmobs): add external experiment recorder”GitHub · Jul 31, 2026 · 2 reactions
- ComposioHQ/composio“chore(deps-dev): bump the npm-development group across 1 directory with 9 updates”GitHub · Nov 6, 2026 · 1 reactions
The biggest 5 of 56 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 56
Talked about on GitHub and Bluesky (56 times).
On GitHub · 49
- Jul 31, 2026feat(llmobs): add external experiment recorder — DataDog/dd-trace-js2 reactions · 5 comments
- Nov 6, 2026chore(deps-dev): bump the npm-development group across 1 directory with 9 updates — ComposioHQ/composio1 reaction · 5 comments
- Nov 3, 2026chore(deps-dev): bump the npm-development group across 1 directory with 8 updates — ComposioHQ/composio1 reaction · 6 comments
- Oct 30, 2026Bump the production-dependencies group across 1 directory with 11 updates — byronwade/rebuzzle.byronwade.com1 reaction · 6 comments
- Oct 30, 2026chore(deps-dev): bump the npm-development group with 7 updates — ComposioHQ/composio1 reaction · 6 comments
44 more on GitHub
- Oct 16, 2026chore(deps-dev): bump the npm-development group across 1 directory with 8 updates — ComposioHQ/composio1 reaction · 6 comments
- Oct 16, 2026chore(deps-dev): bump the npm-development group with 4 updates — ComposioHQ/composio1 reaction · 6 comments
- Oct 13, 2026chore(deps-dev): bump the npm-development group with 3 updates — ComposioHQ/composio1 reaction · 5 comments
- Oct 9, 2026chore(deps-dev): bump the npm-development group across 1 directory with 7 updates — ComposioHQ/composio1 reaction · 6 comments
- Sep 25, 2026chore(deps-dev): bump the npm-development group with 8 updates — ComposioHQ/composio1 reaction · 4 comments
- Sep 14, 2026chore(deps): bump the production-dependencies group across 1 directory with 13 updates — byronwade/rebuzzle.byronwade.com1 reaction · 5 comments
- Sep 11, 2026chore(deps-dev): bump the npm-development group with 5 updates — ComposioHQ/composio1 reaction · 4 comments
- Sep 7, 2026chore(deps): bump the production-dependencies group across 1 directory with 12 updates — byronwade/rebuzzle.byronwade.com1 reaction · 4 comments
- Sep 1, 2026@nuxt/kit missing @nuxt/schema dependency breaks TypeScript with pnpm 12 GVS — nuxt/nuxt1 reaction
- Aug 31, 2026chore(deps): bump the production-dependencies group with 11 updates — byronwade/rebuzzle.byronwade.com1 reaction · 4 comments
- Aug 13, 2026基于 vercel/eve 实现 agents demo 切片 — SawanaLabs/agent-demos1 reaction · 3 comments
- Jul 28, 2026fix(nitro): vercel function rules - preserve relative symlinks — nitrojs/nitro1 reaction · 4 comments
- Jul 3, 2026Add Eve adapter (eve_gateway + eve_local) — paperclipai/paperclip1 reaction · 6 comments
- Jun 30, 2026Install eve skill from vercel/eve — TommyBez/evex1 reaction · 2 comments
- Jun 19, 2026[codex] Read downloads from the sandbox stream — remiconnesson/eve-single-user-agent-starter1 reaction · 1 comment
- Nov 3, 2026[ARCHITECTURE ASSESSMENT] Eve.dev adoption — no control-plane replacement; bounded comparative pilot — mastermindx-market-intelligence/Mastermind0 reactions
- Nov 2, 2026Broken links report — Li-Evan/awesome-jev0 reactions
- Oct 27, 2026Telegram HITL: при нажатии кнопки подтверждения теряется нажавший (auth: null) — в вендоренном eve 0.51.1 нет фикса vercel/eve#4241 — smixs/iva-agent0 reactions · 1 comment
- Oct 26, 2026Broken links report — Li-Evan/awesome-jev0 reactions
- Oct 19, 2026Broken links report — Li-Evan/awesome-jev0 reactions
- Oct 18, 2026T2: Preserve authenticated attachments when continuing copied history — FranciscoMoretti/chat-js0 reactions
- Oct 18, 2026T1/T2: Adopt upstream structured history imports with completed tools and attachments — FranciscoMoretti/chat-js0 reactions
- Oct 17, 2026Research: Eve project primer — setup, models via AI Gateway, approvals, subagents, Next.js mount, deploy — rymanacevedo/business-wiki-agent0 reactions · 2 comments
- Oct 12, 2026Broken links report — Li-Evan/awesome-jev0 reactions
- Oct 11, 2026`vercel dev` stalls silently (no port, no error) when the Next.js dev-manifest config loader exits non-zero — vercel/vercel0 reactions
- Oct 6, 2026Research: custom SPARQL-generation model + separate review layer (prior art: eve + Qwen + Jev data analyst) — wazootech/wazoo-memorybench0 reactions
- Oct 3, 2026[Add] eve (vercel/eve) — PyTorchKR/landscape0 reactions
- Sep 30, 2026Research report - numbered build order, hackathon checklist, runtime pick — VasuBansal7576/return-intelligence-voice0 reactions
- Sep 19, 2026未対応のカードの効果の翻訳を、会話の中で Pull Request として足せるようにする — mokosystem/pokemon-tcg-buddy0 reactions
- Sep 1, 2026sep 2026 — kimtth/azure-openai-llm-notes0 reactions
- Aug 12, 2026Ship an eve and AI SDK memory integration guide — Studio-Moser/Advisaur-MCP0 reactions
- Aug 12, 2026Evaluate eve as a seventh distribution channel — tartinerlabs/skills0 reactions · 2 comments
- Aug 10, 2026epic(ai): the agent harness -- vision, prior art, and the plan to stand behind "or the agent harness itself" — routecraftjs/routecraft0 reactions · 4 comments
- Jul 14, 2026Epic: publish TypeScript SDK and durable Eve approval channel — asiraky/mayi0 reactions · 2 comments
- Jul 13, 2026@ai-sdk/openai: support ordered additional_tools after a normal tool result — vercel/ai0 reactions · 4 comments
- Jul 4, 2026feat(eve): import Agent Runs and OpenTelemetry evidence into fak session ledgers — anthony-chaudhary/fak0 reactions
- Jul 4, 2026test(eve): run eve evals as fak parity and regression witnesses — anthony-chaudhary/fak0 reactions · 7 comments
- Jul 4, 2026feat(eve): lease-gate shared-sandbox subagent fan-out from child session streams — anthony-chaudhary/fak0 reactions · 1 comment
- Jul 4, 2026feat(eve): preflight MCP/OpenAPI connections for scoped auth, allowlists, and approval gates — anthony-chaudhary/fak0 reactions · 1 comment
- Jul 4, 2026feat(eve): compile agent/ directories into fak policy and mount manifests — anthony-chaudhary/fak0 reactions · 1 comment
- Jul 4, 2026epic(eve): Vercel eve integration bridge - filesystem agents, policy lint, evals, and observability — anthony-chaudhary/fak0 reactions
- Jun 23, 2026@vercel/connect/eve: support context-aware Slack installation selection — vercel/vercel0 reactions
- Jun 19, 2026Remove sandbox stream compatibility fix after Eve #117 is released — remiconnesson/eve-single-user-agent-starter0 reactions
- Jun 19, 2026Add Vercel Eve sandbox backend adapter support — sandbox0-ai/sandbox00 reactions
On Bluesky · 7
- Oct 16, 2026@vercel.com Eve #Agentic #framework uses #filesystem as interface for tools, just drop a #TypeScript code into a folder, the filename… — @qdrddr.bsky.social8 likes and reposts · 1 reply
- Jun 17, 2026When frameworks like eve break out, it’s a sign: AI agents are no longer side projects—they’re becoming a new pillar of mainstream software… — @projectnothing.bsky.social3 likes and reposts
- Sep 17, 2026📦 vercel / eve ⭐ 5,184 (+40) 🗒 TypeScript The Open Framework for Building Agents — @github-trending-js.bsky.social2 likes and reposts
- Sep 20, 2026github.com/vercel/eve GitHub - vercel/eve: The Open Framework for Building Agents — @technews4869.bsky.social1 likes and repost
- Aug 11, 2026Cloudflare OS blog: blog.cloudflare.com/cloudflare-os/, github.com/cloudflare/cloudflare-os Vercel eve: vercel.com/blog/introducing-eve ·… — @akash-bhatia.bsky.social1 likes and repost
2 more on Bluesky
- Jul 2, 2026Vercel's eve is a filesystem-first framework for durable AI agents: an agent is a directory of instructions, tools, skills, channels, and… — @agentpalisade.bsky.social1 likes and repost
- Jun 17, 2026The Framework for Building Agents https://github.com/vercel/eve — @laxima-tech.bsky.social1 likes and repost
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository115 other files it gives its agents.
- AGENTS.mdAGENTS.md
- apps/docs/AGENTS.mdAGENTS.md
- apps/templates/eve-agent-python-template/AGENTS.mdAGENTS.md
- apps/templates/eve-agent-python-template/apps/web/AGENTS.mdAGENTS.md
- apps/templates/eve-chat-template/AGENTS.mdAGENTS.md
- apps/templates/eve-coding-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-content-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-contentful-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-data-analyst-template/AGENTS.mdAGENTS.md
- apps/templates/eve-discord-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-llm-council-template/AGENTS.mdAGENTS.md
- apps/templates/eve-mem0-template/AGENTS.mdAGENTS.md
- apps/templates/eve-slack-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-software-factory-template/AGENTS.mdAGENTS.md
- apps/templates/eve-sre-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-tanstack-start-template/AGENTS.mdAGENTS.md
- apps/templates/eve-vercel-drives-starter/AGENTS.mdAGENTS.md
- apps/templates/eve-voice-template/AGENTS.mdAGENTS.md
- apps/templates/kody-eve-template/AGENTS.mdAGENTS.md
- apps/templates/marketing-team-eve-template/AGENTS.mdAGENTS.md
- apps/templates/openinstinct/AGENTS.mdAGENTS.md
- apps/templates/personal-agent-template/AGENTS.mdAGENTS.md
- apps/templates/sanity-copilot-eve-template/AGENTS.mdAGENTS.md
- apps/templates/slack-company-brain-template/AGENTS.mdAGENTS.md
- packages/eve-agent-desktop/AGENTS.mdAGENTS.md
- packages/eve-code/AGENTS.mdAGENTS.md
- packages/eve-computer-use/AGENTS.mdAGENTS.md
- packages/eve-custom-skills/AGENTS.mdAGENTS.md
- packages/eve-git/AGENTS.mdAGENTS.md
- packages/eve/src/internal/nitro/AGENTS.mdAGENTS.md
- apps/templates/eve-agent-python-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-chat-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-coding-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-content-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-contentful-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-data-analyst-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-discord-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-llm-council-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-mem0-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-memory-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-slack-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-software-factory-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-sre-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-tanstack-start-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-vercel-drives-starter/CLAUDE.mdCLAUDE.md
- apps/templates/eve-voice-template/CLAUDE.mdCLAUDE.md
- apps/templates/kody-eve-template/CLAUDE.mdCLAUDE.md
- apps/templates/marketing-team-eve-template/CLAUDE.mdCLAUDE.md
- apps/templates/openinstinct/CLAUDE.mdCLAUDE.md
- apps/templates/personal-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/sanity-copilot-eve-template/CLAUDE.mdCLAUDE.md
- apps/templates/slack-company-brain-template/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- gh-pr-descriptionSkill
- pr-shepherdSkill
- technical-writingSkill
- test-auditSkill
- create-payment-credentialSkill
- dashboard-chat-best-practicesSkill
- eve-chat-template-eveSkill
- The first 60 shown.
The file
We split this AGENTS.md into the rules it gives an agent
8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
Keep discovery bounded: read the routed documentation and the files needed for the change, then implement.
- Very specific: line 40
Prefer native integrations.
- Very specific: line 50
Use .env.example to document new configuration without credentials.
- Very specific: line 61
Keep the Memory section of agent/instructions.md consistent with each slot's description.
- Very specific: line 71
Use the Vercel CLI for project configuration and deployment instructions, including vercel deploy --prod, vercel env add, vercel blob, and …
- Very specific: line 75
Keep README.md concise, with the deployment flow, the technology and customization tables, and short summaries that link to …
- Distinctive: line 77
Write for a person using the template:
- Distinctive: line 84
Keep commands usable in context.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
eve Memory Agent
This repository is a reusable Slack-based assistant built on eve that saves the preferences people share with it. User preferences and channel conventions are stored in separate memory slots and recalled before the agent responds to each message. Use Node.js 24 and pnpm.
These instructions are for agents maintaining the repository. The assistant's behavior is defined in agent/instructions.md and the dynamic instructions under agent/instructions/.
Project map
| Change | Location |
| Assistant behavior, memory rules, and response style | agent/instructions.md |
| Current time context | agent/instructions/current-time.ts |
| Model and session limits | agent/agent.ts |
| Memory slots | agent/memory/user-preferences.ts and agent/memory/channel-preferences.ts |
| Channel memory scope | agent/lib/memory/scope.ts |
| Slack channel, sender auth, and profile lookups | agent/channels/slack.ts and agent/lib/integrations/slack/ |
| HTTP channel and caller auth | agent/channels/eve.ts |
| Built-in tool overrides | agent/tools/ |
| Local and hosted sandbox selection | agent/sandbox.ts |
| Shared test fixtures | agent/lib/testing/ |
| Setup and customization guidance | README.md, CUSTOMIZATION.md, and .env.example |
Keep the template focused on memory. Features such as Slack tables, charts, or approval cards belong in a project built from the template, not in the template itself. Optional extensions, such as shared reference files on Vercel Drives, are documented in CUSTOMIZATION.md and are not enabled by default.
Before implementing changes
Inspect the relevant implementation and nearby tests. For eve API changes, start with the installed documentation index, then read the page it identifies for the task. Memory changes usually need node_modules/eve/docs/memory/. Use eve's published documentation if the installed docs are unavailable. Verify third-party APIs against the installed package or current official documentation rather than relying on recalled signatures.
Keep discovery bounded: read the routed documentation and the files needed for the change, then implement. Follow imports or public types only when they resolve a specific unanswered question. Do not recursively scan dependencies or read unrelated framework pages.
Content-only changes to the assistant's instructions do not require framework research. Preserve the configured model unless changing it is part of the request.
For a new external integration or memory provider, check the eve registry before writing an integration from scratch:
pnpm exec eve registry search <query> --json
pnpm exec eve registry view <item>Prefer native integrations. When installation is part of the task, use pnpm exec eve add <item> --non-interactive. Exit code 2 means setup needs an answer or prerequisite; inspect the final NDJSON event and follow its continuation instructions. Never pass secrets through --answer.
Implementation conventions
Keep files in agent/tools/ small, with reusable behavior in agent/lib/. The template's tool files only disable eve built-ins. Disabling write_file steers the model toward the memory tools. The web and delegation tools are removed because a memory agent doesn't need them and they would give planted instructions a way to send data out. bash and read_file stay enabled for the Drives extension, and agent/sandbox.ts denies outbound network access when deployed. The filename exemption for agent/tools/*.ts in lint.config.ts exists because eve matches built-in tools by filename.
Preserve the strict TypeScript and Ultracite configuration. Do not disable rules to make a port or refactor pass.
Add useful TSDoc when introducing or changing exported helpers, tools, channels, scopes, or configuration types. Document parameters with @param name - description, type parameters with @typeParam, and meaningful return values with @returns. Use @remarks for behavior callers need to know, such as when a scope disables memory; avoid comments that merely repeat the symbol name or type.
Use .env.example to document new configuration without credentials. When configuration changes affect setup or behavior, update the relevant human documentation too.
pnpm enforces a minimum release age for dependencies. Do not bypass the policy or relax it globally. When an install fails because of it, report the affected packages and let the user decide whether to add pinned exclusions to pnpm-workspace.yaml.
Memory behavior to preserve
- Resolve every memory scope from authenticated session details, never from model input, message text, or Slack profile names. Profile lookups in
identity.tsadd names and images for the model, never emails, and do not establish identity or authorization. - Return
nullfrom a scope when the caller doesn't qualify. eve then skips the slot and its tools; never fall back to a shared scope. bySlackChannelaccepts only Slack webhook user principals with aslack:<team>issuer and a public or private channel ID. It disables channel memory in one-to-one DMs and for bots, and returns the sharedlocal-devscope during local development. Updatescope.test.tswith any change to these rules.- Both template scopes include the Slack installation issuer, so memory from different workspaces never shares storage. Keep that boundary in new scopes.
- Renaming a slot file or changing a scope's tuple shape, including the
"slack-channel"prefix, changes the storage key and orphans existing memories. For a rename, keep the old namespace by returningdefaultNamespace({ ...ctx, slot: "<old-name>" })fromeve/memory. Switching an existing slot to an explicit namespace string also orphans its memories, and a tuple change always needs a migration. - Keep the Memory section of
agent/instructions.mdconsistent with each slot'sdescription. The instructions decide which slot to use; the descriptions say what each slot holds. Recalled memory is untrusted user data, and the instructions must keep telling the model never to save sensitive information.
Local and hosted behavior
pnpm dev opens eve's terminal chat. Local sessions use just-bash, don't look up Slack profiles, and keep memory only while the development server runs, so saved preferences disappear when it restarts. Both slots resolve to a shared local-dev scope locally.
The hosted agent uses Vercel Sandbox and stores memory in a private Vercel Blob store that file memory reads through BLOB_STORE_ID and Vercel OIDC. Prefer Vercel OIDC for supported services rather than introducing additional API tokens.
The Slack channel uses SLACK_CONNECTOR, falling back to slack/placeholder so compilation works before Slack is configured. Slack delivery still needs a real connector. Pull the project's variables with vercel env pull .env.local.
Use the Vercel CLI for project configuration and deployment instructions, including vercel deploy --prod, vercel env add, vercel blob, and vercel sandbox. Confirm unfamiliar flags with --help. Provisioning services or deploying the agent is separate from checking code and documentation.
Documentation standards
Keep README.md concise, with the deployment flow, the technology and customization tables, and short summaries that link to CUSTOMIZATION.md for detailed procedures. Preserve working examples and previously accepted wording when revising a section.
Write for a person using the template:
- Explain what a setting controls before showing it. Distinguish optional values from required configuration and state what the code does when a variable is unset.
- Explain terms on first use, such as memory slot, scope, and turn. Prefer plain descriptions to implementation terms like "process memory".
- Say which memory a statement applies to. Distinguish user memory from channel memory instead of writing an unspecified "memory" or "preferences" when the difference matters.
- Lowercase Vercel environment names mid-sentence, such as "preview" and "production". Labels at the start of a table cell keep their capitalization.
- Connect related ideas naturally. Avoid choppy sequences of short sentences, short sentences split off from the reason that explains them, forced groups of three, parenthetical asides, bold lead-ins, colons joining two sentences, and unnecessary emphasis. Do not begin prose sentences with "A" or "An".
- Keep commands usable in context. Identify required input and explain how to recognize success.
Verify behavior against code and current CLI help. When reviewing a passage, read its surrounding section for contradictions and repeated explanations. After applying an edit, check that the revision didn't introduce new problems from the list above. Formatting and link checks do not replace an editorial review.
Validation
pnpm check and pnpm fix use lint.config.ts explicitly to keep its Ultracite rules separate from monorepo linting. .oxfmtrc.json contains the resolved Ultracite formatting preset so root tooling needs no template dependencies. Keep it in sync when upgrading Ultracite. Git hooks are opt-in: run pnpm exec lefthook install only from a standalone checkout, never from the eve monorepo.
Choose checks that establish the changed behavior. Tests live beside their implementations under agent/.
| Command | Purpose |
pnpm check | Formatting and lint rules |
pnpm fix | Apply formatting and lint fixes |
pnpm typecheck | TypeScript checks |
pnpm exec vitest run <test-file> | Tests for the changed behavior |
pnpm validate | Formatting, lint, types, all tests, and unused-code checks |
pnpm exec eve info | Agent diagnostics |
pnpm build | Production compilation |
For code changes, run the relevant tests and static checks. Use pnpm validate for changes spanning several parts of the agent, and run pnpm build when changing memory slots, channels, the sandbox, or other framework registration. Add tests for meaningful behavior changes, especially scope rules.
For documentation-only changes, check formatting and affected links or examples. Typecheck new code samples before adding them to the docs. Do not run the full application test suite for a prose edit. State which checks ran and distinguish source inspection from behavior tested against live services.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

