Harness Bridge
SDK / ToolA local launcher that points Claude Code and seven other coding harnesses at any OpenAI-, Anthropic- or Responses-compatible endpoint — without editing a single config file.
- launcher
- local-models
- cli
- menu-bar
A Datalog engine for LLM agent memory — memory as a deductive database with provenance, not a bigger pile of embeddings.
Lemmalog treats an agent's memory as a verifiable model of what it knows: base facts are asserted at ingestion, rules derive closures and contradiction candidates, every fact carries provenance back to source episodes, and each conversation turn updates derived views incrementally. It ships as a Rust crate, a stdio MCP server (12 tools) for Claude Code and Kimi CLI, a REPL, and an agent skill. The README keeps an honest status log of what shipped versus what's on the roadmap.
For agent builders who need memory that can answer 'how do you know that?' — contradiction detection and provenance matter more than fuzzy recall.
git clone https://github.com/JordyZomer/lemmalog cd lemmalog cargo build --release --features mcp claude mcp add lemmalog -- $(pwd)/target/release/lemmalog-mcp
Early project: leapfrog joins and DBSP streaming deltas are marked future work, and the README's own status log is the source of truth on maturity. Ships as source — clone and compile with cargo.
Repository
JordyZomer/lemmalogCharted
A local launcher that points Claude Code and seven other coding harnesses at any OpenAI-, Anthropic- or Responses-compatible endpoint — without editing a single config file.
Answers macOS Spotlight and Siri prompts with your signed-in Claude Code account — an experimental macOS 27 model-delegation provider.
Extract your own local chat history from ten AI coding assistants into one normalized JSONL — for fine-tuning, analytics, or backing up years of conversations. Standard library only.