ToolRecall — Deterministic Execution Layer for Agent Tools

🌐 toolrecall.dev — documentation, benchmarks, downloads

You run agents. Every session spawns its own MCP servers, every test run hits live APIs, every tool call is unrepeatable, and your agent can read ~/.ssh if it feels like it.

ToolRecall is one shared daemon that pools your MCP servers, records and replays tool results, caches repeated API calls, and enforces filesystem/terminal policy for any agent framework.

One warm daemon instead of five cold Node processes. ~132 KB install. Python 3.11+ stdlib only.

⚠️ Who this is for: ToolRecall's file cache shines for stateless agents (Hermes, OpenCode, Cline, Google ADK) — agents with limited or no built-in context management. If your agent already manages its own context (Claude Code, Cursor), the forward proxy and MCP multiplexer still save real money, but file caching through MCP may increase costs. See Agent Compatibility.

pipx install toolrecall
toolrecall setup          # One-shot: config -> systemd -> daemon start

Zero config mode: Every toolrecall command auto-starts the daemon if it isn't running. You never need to think about it.

Quickstart — MCP Bridge (30 seconds)

Connect any MCP agent by registering one server:

// ~/.claude/settings.json  or  ~/.cursor/mcp.json  or  ~/.config/cline/mcp_settings.json
{
  "mcpServers": {
    "toolrecall": {
      "command": "toolrecall",
      "args": ["mcp"]
    }
  }
}

# ~/.config/toolrecall/toolrecall.toml
[mcp_multiplex]
servers = ["time", "github", "fetch"]

That's it. Your agent now has access to all multiplexed MCP servers, caching, and security — with zero per-agent configuration.

Before: 5 agents x 3 MCP servers = 15 cold Node processes, ~25 MB RAM per server
After:  5 agents x 1 toolrecall mcp = 3 warm subprocesses, shared across all agents

Features:

• Lazy loading: servers boot on first call, not at daemon start
• Idle timeout: inactive subprocesses killed after 15 min (configurable)
• Failure isolation: one server crash doesn't affect others (auto-reconnect)
• Auto-resolution: server names resolve from built-in registry

See MCP Multiplexer for full configuration.

What ToolRecall Does

Full detail in Architecture.

How It Works

flowchart LR
    subgraph Agents
        A1["Claude Code"]
        A2["Cursor"]
        A3["Aider"]
        A4["Hermes"]
    end
    subgraph Daemon["ToolRecall Daemon"]
        MP["MCP Multiplexer"]
        CA["Cache (LRU + SQLite)"]
        SG["Security Gate"]
        FP["Forward Proxy"]
    end
    subgraph OS["OS Layer"]
        FS["Filesystem / Network"]
    end

    A1 --> MP
    A2 --> MP
    A3 --> MP
    A4 --> MP
    MP --> CA
    MP --> SG
    MP <--> FS
    A1 --> FP
    FP --> CA
    FP <--> FS

One daemon, five access paths: Python client, MCP bridge, HTTP bridge, forward proxy, OS-level shim. All share one cache, one security gate, one multiplexer. See Architecture.

When To Use It

|| You want this... | Use this... | Works for | ||-----------------|-------------|-----------| || Warm MCP servers across sessions | MCP Multiplexer | Any agent | || $0 dev loops — repeated API calls cost nothing | Forward Proxy | Any agent | || Deterministic CI tests for agent behavior | Replay Mode | Any agent | || Guardrails between agents and your machine | Security Gate | Any agent | ||| Cached file reads, lower context bloat | File / Terminal Cache | Stateless agents (Hermes, Cline, ADK) — measured 73-91% fewer repeat tokens. Not for agents with built-in context management | || All of the above | toolrecall setup then add the MCP bridge | See per-agent notes |

Installation

One-time setup

pipx install toolrecall        # or: uv tool install toolrecall
                               # or: pip install toolrecall (inside a venv)
toolrecall setup                # config -> systemd service -> daemon start

PATH check: After installation, make sure toolrecall is on your $PATH.
pipx puts binaries in ~/.local/bin/, uv tool install in ~/.local/share/uv/tools/.
If toolrecall isn't found, add the right directory to your PATH or reinstall inside the venv your agent uses.

Shim in the right venv: toolrecall shim --install installs the .pth shim into the current Python environment. If you installed via pipx or uv tool install, the shim goes into that isolated environment — not your agent's venv. The agent won't see it. toolrecall setup auto-detects common agent venvs and installs the shim there too. toolrecall shim --install --all scans for agent venvs (Hermes, OpenCode) and installs into all of them at once. If you need to target a specific venv manually:

toolrecall shim --install --venv ~/.hermes/hermes-agent/venv
toolrecall shim --install --venv ~/.local/share/uv/tools/hermes-agent

The toolrecall package must also be installed in that venv (import toolrecall must work).

toolrecall setup creates ~/.config/toolrecall/toolrecall.toml with default-deny security, generates a systemd user unit, and starts the daemon. After this, every toolrecall command "just works".

Daemon auto-start fallback: systemd -> os.fork() -> DETACHED_PROCESS (Linux -> Docker/macOS -> Windows).

Per-agent integration

Extra storage backends

pip install toolrecall[libsql]       # libSQL local backend
pip install toolrecall[libsql-sync]  # libSQL + Turso Cloud sync

CLI Quick Reference

toolrecall setup          One-shot: config + systemd + daemon start  [required once]
toolrecall status         Cache status and stats                     [auto-starts]
toolrecall stats          Detailed cache statistics (JSON)           [auto-starts]
toolrecall invalidate     Clear all caches                           [auto-starts]
toolrecall mcp            Start MCP Bridge                           [auto-starts]
toolrecall serve          Forward proxy (cache API responses)        [auto-starts]
toolrecall serve --9000   Custom port forward proxy
toolrecall replay         Record/replay agent sessions
toolrecall shim --install Install OS-level cache shim (.pth file)
toolrecall turso          Turso Cloud sync: init, enable, disable, status
toolrecall init           Create default config.toml and .env
toolrecall config-set     Set a config value
toolrecall index          Index knowledge DB (FTS5 search)  [not file cache pre-warm]
toolrecall index-memory   Index agent memory stores
toolrecall index-dir      Index a directory for FTS5 search [not file cache pre-warm]

Knowledge indexing ≠ cache warming: toolrecall index* commands build an FTS5 search index for knowledge retrieval (docs_search()). They do NOT pre-warm the file/terminal/API response cache. The daemon's file cache warms naturally as the agent reads files — no separate command needed.

Full reference: CLI.md

Configuration

# ~/.config/toolrecall/toolrecall.toml
[mcp]
allowed_paths = ["/home/user/projects"]  # Default-deny!
allow_terminal = false

[cache]
terminal_default_ttl = 60

[mcp_multiplex]
enabled = true
servers = ["time", "sequential-thinking"]

[forward_proxy]
# Starts on :8569 automatically with the daemon

TOOLRECALL_* env vars override TOML. Full reference: Configuration Reference

Platform Support

Documentation

• toolrecall.dev — documentation portal, benchmarks, downloads
• Architecture — system design, components, data flow, token costs
• MCP Multiplexer — daemon-managed MCP server pool
• Forward Proxy — API response caching, provider list, auth routing
• Replay Mode — record/replay tool calls for deterministic CI
• Security Architecture — policy gate, trust boundary
• Agent Compatibility — per-agent value, config, caveats
• Benchmark — three-arm controlled measurement (naive vs prefix vs toolrecall), context efficiency, billed cost
• Bench Infrastructure — reproduce the three-arm benchmark
• Test Suite — test runner documentation
• CLI Reference — all subcommands
• Configuration Reference — config.toml, env vars
• Context Stale — provably stale files in agent conversations
• Context Tracker — checkpoint-based dirty-file tracking
• AGENTS.md — agent instructions for MCP context tracker integration
• Testing Guide — test philosophy, per-file coverage
• How It Works — quick technical overview
• libSQL Backend — multi-writer, vector search, cloud sync
• Docker Deployment — containerized stack
• Troubleshooting — common fixes
• Changelog — version history
• Go Client — standalone tr binary for any language/shell
• Agent Configs — ready-to-use MCP configs for popular agents
• Framework Adapters:
  • Google ADK — @cached_tool decorator + forward proxy
  • LangChain / LangGraph — ToolRecallCache BaseCache + callback
  • herdr — tr binary + MCP bridge for any pane
  • Odysseus — cached_tool decorator + MCP server caching
• Hermes Transparent Cache — auto-patching for Hermes
• Normalizer — cache key normalization, deterministic JSON
• Knowledge DB — FTS5 indexing guide
• Real-Agent Benchmark — edit-heavy session results
• Appendix — comparison tables, OSI model, ROI, audit

Contributing

git clone https://github.com/whiskybeer/toolrecall.git
cd toolrecall
make setup    # one-time dev deps
make test     # run tests
make check    # lint + format

See Testing Guide and Makefile.

Uninstall

systemctl --user stop toolrecall-daemon
systemctl --user disable toolrecall-daemon
pipx uninstall toolrecall
rm -rf ~/.toolrecall ~/.config/toolrecall