Builderforce Memory
Token-saving persistent memory for AI agents: recall durable facts instead of re-reading files.
Connector by SeanHogg · GitHub account verified by the MCP Registry
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/seanhogg-builderforce-memory
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.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.
- Tools
- 3 read · 1 write · 1 delete · 4 not yet classified
- Secrets
- 1 (API keys, tokens or passwords)
- Install scripts
- None found
- Runs as
- Node.js package
Tools by what they do 9
Read from the source code; the running server may list different tools.
Read 3 · Look things up without changing anything.
memory_getmemory_recallmemory_recall_by_tag
Write 1 · Create, change, send or run things.
memory_restore
Delete 1 · Delete, drop, revoke or wipe things.
memory_forget
Not yet classified 4 · We could not tell from the name and description.
memory_compactmemory_remembermodel_efficiencytoken_usage
Secrets and settings it asks for
Secrets: values you paste in that let it act as you.
BUILDERFORCE_API_KEY
Other settings (environment variables or headers).
BUILDERFORCE_MEMORY_FILEBUILDERFORCE_MEMORY_READONLY
Network hosts it talks to 3
api.builderforce.ai· found in codebuilderforce.ai· found in codegithub.com· found in code
Files it touches
- Your home directory (~)
Tools (9)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
memory_compactShrink memories that have already been absorbed into the local Evermind model down to a one-line pointer stub, reclaiming the context they were eating. Each fact is first checked with a recall question put to the model; facts it cannot answer stay as they are. The full original is archived and memory_recall / memory_get still return it, so nothing is lost. Already-compacted keys are skipped, so repeating the call is safe.
memory_forgetDelete a memory by key. Use to remove a fact that is now wrong or obsolete.
memory_getFetch a single memory by its exact key. Use when you already know the key (e.g. one surfaced by memory_recall) and want its full, untruncated value.
memory_recallSemantically recall the most relevant stored memories for a query. Call this BEFORE answering whenever the task may depend on prior context, user preferences, project decisions, or facts learned in earlier sessions — instead of assuming that context is already in your prompt. Returns a small ranked set, not the whole store.
memory_recall_by_tagList memories carrying a given tag (e.g. 'user', 'project', 'decision'). Use to pull a known category of context rather than searching semantically.
memory_rememberPersist a fact for future sessions. Call when you learn something durable and reusable: a user preference, a project constraint, a decision and its rationale. Keep keys stable and descriptive (e.g. 'user.preferred-language') so the same fact overwrites rather than duplicating.
memory_restoreRestore the full text of memories marked '(content lost)' — compaction stubs whose original was never kept — from an export. Accepts [{key, content}] (a memory export) or the Evermind coordinator's [{id, text}] record dump; records are matched by key, else by their first line against the stub. Restored memories recall in full again.
model_efficiencyWhich models performed best/cheapest for this workspace's recent work.
token_usageCurrent token spend + budget for the workspace (today).
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (6 days ago)
- Last release
- Oct 25, 2026 (4 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Registry name
io.github.SeanHogg/builderforce-memory- Version
- 2026.10.26
- Auth
- API key
- Packages
- npm @seanhogg/builderforce-memory-mcp
- License
- License unknown
- Repository
- github.com/SeanHogg/builderforce-memory
- Website
- builderforce.ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 26, 2026
More from SeanHogg
Cite this page
Builderforce Memory MCP server. Agent Mart. https://agentmart.dev/connectors/seanhogg-builderforce-memory (last updated 2026-10-26)