claude-webcache

Persistent cross-session WebFetch cache for Claude Code. Cached reads in ~0.05ms — orders of magnitude faster than re-fetching.

Claude Code's built-in cache lasts 15 minutes, within one session. Every new session re-fetches from scratch. claude-webcache persists results across sessions in a local SQLite database — instant cache hits, zero network cost.

Session 1  →  WebFetch("docs.example.com")  →  fetched, auto-cached ✓
Session 2  →  cached_fetch("docs.example.com")  →  instant hit, no network call
Session 7  →  cached_fetch("docs.example.com")  →  still instant, unlimited TTL

v0.1.5+: every WebFetch is automatically saved via PostToolUse hook — nothing to configure.

Install

claude plugin marketplace add theYahia/claude-webcache && claude plugin install claude-webcache@theyahia

Works in: Claude Code CLI · Desktop (Mac/Windows) · VS Code extension · JetBrains plugin — same command everywhere.

Done. Every WebFetch is auto-cached from now on.

Optionally add the usage pattern to ~/.claude/CLAUDE.md to also check the cache before fetching (saves the WebFetch call entirely on repeat URLs).

Plugin TUI not working? There's an open Claude Code bug (#41653) where /plugin install rejects third-party sources with "source type not supported." Use the CLI command above — it bypasses the TUI and works fine.

Fallback (no marketplace):

git clone https://github.com/theYahia/claude-webcache && claude --plugin-dir ./claude-webcache/plugin

Option 2 — npm global

npm i -g @theyahia/claude-webcache

Requires Node.js 22.5+ (uses built-in node:sqlite — no native deps, no install step).

Then register in ~/.claude/settings.json (replace path with output of npm root -g):

{
  "mcpServers": {
    "claude-webcache": {
      "command": "node",
      "args": ["/path/from/npm-root-g/claude-webcache/scripts/mcp-server.cjs"]
    }
  },
  "hooks": {
    "SessionStart": [
      {
        "matcher": "startup|clear|compact",
        "hooks": [
          { "type": "command", "command": "node /path/from/npm-root-g/claude-webcache/scripts/hook-stats.cjs" }
        ]
      }
    ]
  }
}

Option 3 — clone (contributors)

See CONTRIBUTING.md.

Usage pattern (optional — for pre-fetch cache checks)

v0.1.5+ auto-caches every WebFetch automatically. The pattern below is optional: add it to ~/.claude/CLAUDE.md to also check the cache before making a WebFetch — this saves the WebFetch call entirely on repeat URLs.

## WebFetch caching (claude-webcache)

Before calling WebFetch, call `cached_fetch(url, prompt)` first.
- If it returns text → use that, do NOT call WebFetch.
- If it returns `[CACHE_MISS] <url>` → call WebFetch as normal (it will be auto-cached for next time).

Same URL + same prompt in any future session = instant hit, zero network cost.

Tools (MCP)

SessionStart hook

Every new session injects a one-liner so Claude knows the cache exists:

webcache: 142 pages cached, 38 hits, last fetch 3h ago

No output if cache is empty.

Storage

SQLite at ~/.webcache/cache.db (WAL mode, concurrent-safe).
Cache key = SHA256(url + "|" + prompt). Default TTL: unlimited (set WEBCACHE_TTL_DAYS=N for N-day expiry).

Limits

• Cache key includes the prompt — use consistent prompts to maximize hit rate.
• Output is whatever WebFetch returns (already summarized). No re-processing.
• No semantic search. Exact (url, prompt) match only.

Benchmarks

Single-process latency on a populated DB (N=10000 entries, 1KB output each), measured via npm run bench:

Storage overhead: ~1.9 KB per entry for a 1 KB payload (extra ≈ key + indexes + WAL).

WebFetch over the network typically takes 1-5 seconds — a cached hit is ~20,000-100,000× faster. Reproduce on your hardware: npm run bench. See bench/README.md for methodology and full results metadata (CPU, RAM, OS, commit) saved per run.

Related

• claude-mem — persistent memory across sessions (complements claude-webcache: memory vs. web cache)
• WWmcp — catalog of 120+ MCP servers for non-Western APIs

License

MIT — see LICENSE.