claude-session-index

Indexes Claude Code session JSONL files from ~/.claude/projects/ into a local SQLite database (with FTS5) to enable fast full-text search, retrieval of conversation excerpts, analytics over usage, and cross-session synthesis (optionally using the Anthropic SDK for standalone synthesize). It can also capture live “topics” during sessions via Claude Code hooks and runs background indexing to keep the index up to date.

Evaluated Mar 30, 2026 (0d ago)
Repo ↗ DevTools developer-tools cli search sqlite fts5 analytics ai claude claude-code session-management
⚙ Agent Friendliness
45
/ 100
Can an agent use this?
🔒 Security
47
/ 100
Is it safe for agents?
⚡ Reliability
39
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
75
Error Messages
0
Auth Simplicity
100
Rate Limits
0

🔒 Security

TLS Enforcement
100
Auth Strength
20
Scope Granularity
20
Dep. Hygiene
40
Secret Handling
60

Security posture is largely local/offline: core indexing/search requires no auth and uses a local SQLite DB. However, the tool indexes conversation content and retrieves excerpts, which increases risk of sensitive data exposure if the local machine/DB is compromised or shared. Optional Anthropic synthesis implies handling an API key (not detailed here). No information is provided about TLS (likely irrelevant for local operation), database encryption, retention policies, file permission hardening, or structured error/safety controls.

⚡ Reliability

Uptime/SLA
0
Version Stability
55
Breaking Changes
60
Error Recovery
40
AF Security Reliability

Best When

You have many local Claude Code sessions stored as JSONL and want a fast local way to search, review, and analyze them using a CLI/Claude Code skill workflow.

Avoid When

You cannot store or index your Claude Code conversation data locally, or you need a standards-based remote API with formal guarantees about security, retention, and access control.

Use Cases

  • Find what you tried last time for a specific issue/tool/topic across many Claude Code sessions
  • Retrieve conversation exchanges and context from a session by search term
  • Analyze usage trends (time by client, tool usage, session frequency, weekly/monthly stats)
  • Create cross-session summaries/synthesis of approaches tried for a given topic
  • Maintain an up-to-date local index automatically via incremental/background indexing
  • Tag and label sessions by client/project names using config

Not For

  • Multi-user hosted/shared server use without additional infrastructure (it’s local/offline oriented)
  • Cases requiring a remote API, webhooks, or managed hosting/SLA
  • Highly regulated environments that require explicit security controls/auditable guarantees not documented here
  • Avoiding local storage of sensitive conversation data (indexing stores excerpts/metadata locally)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
No
SDK
No
Webhooks
No

Authentication

Methods: No authentication required for core local indexing/search CLI/skill operations
OAuth: No Scopes: No

Optional standalone `sessions synthesize` requires an Anthropic package and an API key, but this is not described as part of a network service interface; core functionality is local with no auth layer.

Pricing

Free tier: No
Requires CC: No

No hosted pricing described; package is installed locally via pip and runs on the user’s machine.

Agent Metadata

Pagination
none
Idempotent
True
Retry Guidance
Not documented

Known Gotchas

  • No MCP/REST interface: agent integration relies on CLI/skill execution rather than programmatic network calls.
  • Local filesystem paths and permissions matter (index location, read access to ~/.claude/projects/, launch agent permissions on macOS).
  • Synthesis requires Anthropic SDK/API key for standalone use; omitting or misconfiguring it may break only the synthesize path.
  • FTS5 requires SQLite features; behavior if FTS5 is unavailable/disabled on some environments is not documented.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for claude-session-index.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6533
Packages Evaluated
19870
Need Evaluation
586
Need Re-evaluation
Community Powered