AutomationSoftware development
recall-loom
Preserve project context, decisions, and next steps across AI coding sessions.
- Stars
- 147
- Forks
- 4
- Updated
- Updated Jul 13, 2026
Apache-2.0
Preserve project context, decisions, and next steps across AI coding sessions.
RecallLoom adds a file-based memory layer to long-running AI work, storing project background, current progress, key decisions, and next steps in Markdown and JSON beside the project. When users switch sessions, models, or coding tools, a new agent can restore the controlled current state before continuing, record progress, and check whether continuity files are missing, stale, or conflicting. It is deliberately focused on project continuity, not repository-wide knowledge retrieval, task orchestration, or autonomous execution.
Resource types
Use cases
Platforms
Drive Codex toward measurable code goals while reverting failed experiments automatically.
Turn an arXiv paper into cited code with explicit uncertainty notes.
Runtime
Capabilities
Audience
Public GitHub facts last synced Jul 14, 2026.
Run agent code, builds, hosting, and browser tests inside isolated E2B sandboxes.
Turn a rough coding idea into a measurable contract for long Codex runs.