Skip to content

Tags: Avijit07x/claude-db

Tags

v0.2.3

Toggle v0.2.3's commit message
0.2.3

v0.2.2

Toggle v0.2.2's commit message
0.2.2

v0.2.1

Toggle v0.2.1's commit message
0.2.1

v0.2.0

Toggle v0.2.0's commit message
0.2.0

v0.1.1

Toggle v0.1.1's commit message
0.1.1

v0.1.0

Toggle v0.1.0's commit message
feat: persistent memory for Claude Code, backed by any database

Records why decisions were made across sessions and injects them back
automatically, so architecture and rationale never need re-explaining.

Capture reads Claude Code's session transcripts rather than watching tool
calls. A hook sees a file path; the transcript has the prompt and the
agent's reasoning, which is the part worth remembering.

Observation ids are derived from content (session + turn timestamp +
prompt), so reprocessing rewrites a row instead of duplicating it. That
makes flushing idempotent, which is what allows memory to be written on
every prompt rather than only at SessionEnd. A byte cursor per session
means each flush parses only the new tail.

Recall is not left to the model. SessionStart injects recent summaries and
UserPromptSubmit injects the best match in full, so reasoning is in context
before the agent decides anything.

Storage is one MemoryStore interface with three adapters; the connection
string picks the backend. SQLite via Node's builtin node:sqlite, so there
is no native build step.

Includes MCP tools with three-layer progressive disclosure, hybrid search
fused by reciprocal rank, a zero-dependency local embedder, secret
redaction, GitHub Actions CI and release automation, and 87 tests.