Deterministic code map for AI coding agents: a tree-sitter symbol and call graph served over MCP and a CLI, with no embeddings, network or telemetry.

Cross-session plaintext memory plugin for the DeepSeek Harness — deterministic BM25 recall, writes take effect immediately, signal-driven injection, no embeddings

Platform binary for @dayone/cli (Linux x64, no embeddings)

Semantic grep: describe the code you want in English, get file:line hits. Powered by TypeSafe Jev. No index, no embeddings, no dependencies.

Platform binary for @dayone/cli (Linux arm64, no embeddings)

Self-maintaining codebase memory for AI coding agents: an AST index that answers which files matter, plus agent-written notes that flag themselves stale when the code changes. No embeddings, no API key. CLI + MCP.

Deterministic chart/ask memory for coding agents — lexical-only fork of capn-hook: BM25 recall, no embeddings, no hooks

CLI that matches an error to upstream GitHub issues, traces the fixing PR to the first npm release that ships it, and checks your lockfile. No LLM, no embeddings.

Deterministic structural code intelligence — lexical-only fork of codedb: outline, symbol, call graph, and trigram search. No embeddings, no telemetry, no cloud, no daemon.

Auto-generate code metadata sidecars for LLM-optimized navigation. No AST dumps, no embeddings — just structured YAML.

Local, model-free memory for AI coding agents. Shared across Claude Code, Cursor and Antigravity. No embeddings, no API keys, nothing leaves your machine.

DeepSeek Harness (DSH) local-first cross-session project memory: bounded cache-friendly Hot Memory, BM25 recall/cache, provenance, lifecycle and bilingual Web GUI; no embeddings, external service or bundled runtime dependencies.

Pure, zero-runtime knowledge adapter: implements @agentproto/knowledge-engine's IKnowledgeProvider over local files with an in-process BM25 index (no embeddings, no network, no API key). Registers as a provider-kit family and ships a node:fs FsPort so it

Local-first context engine for AI coding agents: three persistent graphs (code, project memory, trial-and-error knowledge), deterministic retrieval, native OpenCode plugin. No LLM, no embeddings, no network.

Geometric memory for AI coding agents. No embeddings, no vectors, no cloud - just math.

Model-agnostic code memory MCP server. Budget-aware graph retrieval for AI agents — sub-millisecond queries, token budgeting, no embeddings, no API keys. Built on CodeGraphContext for 155-language tree-sitter indexing.

Pi coding agent extension for a file-based, no-embeddings long-term memory system — indexed long-term memory files, recall selection, daily logs, scratchpad checklist, and background consolidation

Grounded GitHub repo discovery MCP server — live keyword search, no embeddings, no backend.

Platform binary for @dayone/cli (macOS x64, no embeddings)

Isomorphic storage client for Supabase.