Lore
Local semantic search engine for software patterns served to AI agents over MCP.
Tested on Linux
Use it
Linux x86_64
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/SHA256SUMSVerify 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/SHA256SUMSsha256sum -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 --versionlore --helpmkdir -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.tomlcat > /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.tomllore search "error handling" --config /tmp/lore.tomlCheck that it works
lore --helpThe 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.tomlcat > /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.tomllore search "error handling" --config /tmp/lore.tomlAdd 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 searchNot tested
- Serve patterns to AI agents over MCPNot tested
- Create and index pattern filesNot tested
How far pickfit got
Linux x86_64
- Installs
- Connects
- A tool call works
- 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