pickfit

BrowseMCP servers

Lore

Local semantic search engine for software patterns served to AI agents over MCP.

Tested on Linux

Use it

Linux x86_64

  1. Download prebuilt lore archive and SHA256SUMS

    curl -LO https://github.com/attila/lore/releases/download/v0.5.0/lore-0.5.0-x86_64-unknown-linux-gnu.tar.gz && curl -LO https://github.com/attila/lore/releases/download/v0.5.0/SHA256SUMS
  2. Verify checksum, extract, install lore to ~/.local/bin

    sha256sum -c SHA256SUMS --ignore-missing && tar xzf lore-0.5.0-x86_64-unknown-linux-gnu.tar.gz && mkdir -p ~/.local/bin && mv lore ~/.local/bin/ && lore --version
Where the README and reality differ
  • README: Set hybrid=false to skip the embedding server
    What worked: Manual lore.toml with [ollama] section plus [search] hybrid=false still attempts embeddings at ingest time (warns embedding failure(s)) but ingest exits 0 and FTS search works offline; lore init itself requires a running Ollama server
Verified in pickfit: the commands exactly as its sandbox ran them

For the record only: they name the sandbox's home, /home/sbx.

curl -LO https://github.com/attila/lore/releases/download/v0.5.0/lore-0.5.0-x86_64-unknown-linux-gnu.tar.gz && curl -LO https://github.com/attila/lore/releases/download/v0.5.0/SHA256SUMS
sha256sum -c SHA256SUMS --ignore-missing && tar xzf lore-0.5.0-x86_64-unknown-linux-gnu.tar.gz && mkdir -p ~/.local/bin && mv lore ~/.local/bin/ && lore --version
lore --help
mkdir -p ~/lore-kb ~/lore-data && cat > ~/lore-kb/error-handling.md <<'EOF'
---
tags: [error-handling, rust, result-types]
---

# Error Handling with Result Types

Always use Result<T, E> for fallible operations.

## Context

Use this pattern for error handling in Rust code.

## Rule

Prefer `?` operator and `thiserror` for error propagation.
EOF
cat ~/lore-kb/error-handling.md
cat > /tmp/lore.toml <<'EOF'
knowledge_dir = "/home/sbx/lore-kb"
database = "/home/sbx/lore-data/knowledge.db"
bind = "localhost:3100"

[search]
hybrid = false
top_k = 5
min_relevance = 0.0
EOF
cat /tmp/lore.toml
cat > /tmp/lore.toml <<'EOF'
knowledge_dir = "/home/sbx/lore-kb"
database = "/home/sbx/lore-data/knowledge.db"
bind = "localhost:3100"

[ollama]
host = "http://127.0.0.1:11434"
model = "nomic-embed-text"

[search]
hybrid = false
top_k = 5
min_relevance = 0.0

[chunking]
strategy = "heading"
max_tokens = 1024
EOF
cat /tmp/lore.toml && lore ingest --config /tmp/lore.toml
lore search "error handling" --config /tmp/lore.toml

Check that it works

lore --help

The output should contain “Local semantic search for your software patterns”.

First thing to try

mkdir -p ~/lore-kb ~/lore-data && cat > ~/lore-kb/error-handling.md <<'EOF'
---
tags: [error-handling, rust, result-types]
---

# Error Handling with Result Types

Always use Result<T, E> for fallible operations.

## Context

Use this pattern for error handling in Rust code.

## Rule

Prefer `?` operator and `thiserror` for error propagation.
EOF
cat ~/lore-kb/error-handling.md
cat > /tmp/lore.toml <<'EOF'
knowledge_dir = "$HOME/lore-kb"
database = "$HOME/lore-data/knowledge.db"
bind = "localhost:3100"

[search]
hybrid = false
top_k = 5
min_relevance = 0.0
EOF
cat /tmp/lore.toml
cat > /tmp/lore.toml <<'EOF'
knowledge_dir = "$HOME/lore-kb"
database = "$HOME/lore-data/knowledge.db"
bind = "localhost:3100"

[ollama]
host = "http://127.0.0.1:11434"
model = "nomic-embed-text"

[search]
hybrid = false
top_k = 5
min_relevance = 0.0

[chunking]
strategy = "heading"
max_tokens = 1024
EOF
cat /tmp/lore.toml && lore ingest --config /tmp/lore.toml
lore search "error handling" --config /tmp/lore.toml

Add it to your agent

claude mcp add lore -- lore serve --config '<config>'
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "lore": {
      "command": "lore",
      "args": [
        "serve",
        "--config",
        "<config>"
      ]
    }
  }
}

Replace <config> with your own path.

Run lore search "<your query>" --config <file> to search your patterns, or connect an MCP client to Lore to use its tools.

What it does

These come from the README; pickfit didn’t check them one by one.

  • Search patterns with semantic and keyword search
    Not tested
  • Serve patterns to AI agents over MCP
    Not tested
  • Create and index pattern files
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Connects
  3. A tool call works
  4. Works offline

macOS: the project says it runs there; pickfit hasn’t tried it.

Good for

  • search software patterns with semantic and keyword search
  • create and index a new pattern file
  • re-index knowledge directory after editing markdown files
  • list every indexed pattern
  • check health of all components

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

An MCP client connects and lists its tools

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 0.5.0

An MCP client handshake over stdio listed 6 tools.

Differences the test machine hit

  • README: cargo install --path .
    In the test: Used prebuilt release archive lore-0.5.0-x86_64-unknown-linux-gnu.tar.gz: verify SHA256SUMS, extract, move lore to ~/.local/bin; cargo candidate needs Rust toolchain which must not be installed in the box
  • README: lore status checks health
    In the test: lore status report is printed to stderr with exit 0, not stdout

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.