memex

Fast local history search for Claude, Codex CLI & OpenCode logs. Uses BM-25 and optionally embeds your transcripts locally for hybrid search.

Mostly intended for agents to use via skill. The intended workflow is to ask agent about a previous session & then the agent can narrow things down & retrieve history as needed.

Includes a TUI for browsing, finding and resuming both agent CLI sessions.

Install

brew install nicosuave/tap/memex

Or

curl -fsSL https://raw.githubusercontent.com/nicosuave/memex/main/scripts/setup.sh | sh

Or (from the AUR on Arch Linux):

paru -S memex

Or (with Nix):

nix run github:nicosuave/memex

Development shell:

nix develop

Note: No binary cache is configured, so first builds compile from source.

NixOS service:

Enable background indexing with the provided module:

{
  inputs.memex.url = "github:nicosuave/memex";

  outputs = { nixpkgs, memex, ... }: {
    nixosConfigurations.default = nixpkgs.lib.nixosSystem {
      modules = [
        memex.nixosModules.default
        {
          services.memex = {
            enable = true;
            continuous = true; # Run as a daemon (optional)
          };
        }
      ];
    };
  };
}

Home Manager:

Configure memex declaratively (generates ~/.memex/config.toml):

{
  inputs.memex.url = "github:nicosuave/memex";

  outputs = { memex, ... }: {
    # Inside your Home Manager configuration
    modules = [
      memex.homeManagerModules.default
      {
        programs.memex = {
          enable = true;
          settings = {
            embeddings = true;
            model = "minilm";
            execution_provider = "auto"; # coreml on macOS, cpu elsewhere
            cuda_device_id = 0; # optional when execution_provider = "cuda"
            cuda_library_paths = ["/usr/local/cuda/lib64"]; # optional override
            cudnn_library_paths = ["/usr/lib/x86_64-linux-gnu"]; # optional override
            compute_units = "ane"; # CoreML only: ane, gpu, cpu, all
            auto_index_on_search = true;
            index_service_interval = 3600;
          };
        };
      }
    ];
  };
}

Then run setup to install the skills:

memex setup

Restart Claude/Codex after setup.

Quickstart

Index (incremental):

memex index

Search (JSONL default):

memex search "your query" --limit 20

TUI:

memex tui

Notes:

• Embeddings are enabled by default.
• Searches run an incremental reindex by default (configurable).

Full transcript:

memex session <session_id>

Single record:

memex show <doc_id>

Human output:

memex search "your query" -v

Build from source

cargo build --release

Linux with NVIDIA CUDA support:

cargo build --release --features cuda

Binary:

./target/release/memex

Setup (manual)

If you built from source, run setup to install:

memex setup

This detects which tools are installed (Claude/Codex) and presents an interactive menu to select which to configure.

Search modes

Common filters

• --project <name>
• --role <user|assistant|tool_use|tool_result>
• --tool <tool_name>
• --session <session_id>
• --source claude|codex
• --since <iso|unix> / --until <iso|unix>
• --limit <n>
• --min-score <float>
• --sort score|ts
• --top-n-per-session <n>
• --unique-session
• --fields score,ts,doc_id,session_id,snippet
• --json-array

Background index service

Works on macOS (launchd) and Linux (systemd).

Enable:

memex index-service enable
memex index-service enable --continuous

Disable:

memex index-service disable

index-service reads config defaults (mode, interval, log paths). Flags override.

On Linux, creates systemd user units in ~/.config/systemd/user/. On macOS, creates a launchd plist in ~/.memex/.

Embeddings

Disable:

memex index --no-embeddings

Recommended when embeddings are on (especially non-potion models): run the background
index service or index --watch, and consider setting auto_index_on_search = false
to keep searches fast.

Embedding model

Select via --model flag or MEMEX_MODEL env var:

memex index --model minilm
# or
MEMEX_MODEL=minilm memex index

Execution provider

Select via execution_provider in config or MEMEX_EXECUTION_PROVIDER:

When execution_provider = "cuda", you can optionally select a GPU with
cuda_device_id or MEMEX_CUDA_DEVICE_ID.

When loading CUDA, memex first tries the system loader paths, then any
configured cuda_library_paths / cudnn_library_paths, then common CUDA install
locations and active venv / conda site-packages/nvidia/*/lib directories.
If your system keeps CUDA or cuDNN in a nonstandard location, set
MEMEX_CUDA_LIBRARY_PATHS and MEMEX_CUDNN_LIBRARY_PATHS or the matching config
keys.

Config (optional)

Create ~/.memex/config.toml (or <root>/config.toml if you use --root):

embeddings = true
auto_index_on_search = true
model = "minilm"  # minilm, bge, nomic, gemma, potion
execution_provider = "auto"  # auto, cpu, coreml, cuda
cuda_device_id = 0  # optional, when execution_provider = "cuda"
cuda_library_paths = ["/usr/local/cuda/lib64"]  # optional list of CUDA library dirs
cudnn_library_paths = ["/usr/lib/x86_64-linux-gnu"]  # optional list of cuDNN library dirs
compute_units = "ane"  # CoreML only: ane, gpu, cpu, all
scan_cache_ttl = 3600  # seconds (default 1 hour)
index_service_mode = "interval"  # interval or continuous
index_service_interval = 3600  # seconds (ignored when mode = "continuous")
index_service_poll_interval = 30  # seconds
index_service_label = "memex-index"  # service name (default: com.memex.index on macOS)
index_service_systemd_dir = "~/.config/systemd/user"  # Linux only
claude_resume_cmd = "claude --resume {session_id}"
codex_resume_cmd = "codex resume {session_id}"

Service logs and the plist live under ~/.memex by default (macOS). On Linux, systemd units are created in ~/.config/systemd/user/.

scan_cache_ttl controls how long auto-indexing considers scans fresh.
execution_provider applies to ONNX-backed models; potion uses the model2vec backend.
cuda_library_paths and cudnn_library_paths accept path lists and are only used
when execution_provider = "cuda".

Resume command templates accept {session_id}, {project}, {source}, {source_path}, {source_dir}, {cwd}.

The skill definitions are bundled in skills/.