This repository was archived by the owner on Feb 1, 2026. It is now read-only.
feat: Add Ollama-based semantic memory system#102
Merged
Conversation
Adds semantic memory integration using Ollama embeddings (nomic-embed-text) for context-aware learning retrieval in Claude Code sessions. Components added: - src/semantic/ - Flask daemon for embedding storage/recall - daemon.py - /store, /recall, /health, /stats, /migrate-heuristics endpoints - install.sh, start-daemon.sh - Installation and startup scripts - systemd service file for Linux deployment - Comprehensive test suite (unit, integration, e2e, load tests) - src/hooks/semantic-hooks/ - Claude Code hook scripts - UserPromptSubmit.sh - Injects relevant memories on each prompt - PreCompact.sh - Captures session before context compaction - Stop.sh - Captures session on clean exit - src/hooks/windows/ - Windows PowerShell equivalents - Full feature parity with bash versions - .ps1 scripts + .cmd wrappers - Installation and test utilities - apps/dashboard/backend/routers/semantic.py - Dashboard API integration - Store/recall/health/stats/migrate endpoints via REST - data/seed_heuristics.json - Initial heuristics export (6 rules) This is an alternative to the sentence-transformers approach, using Ollama for local embeddings without requiring cloud API keys. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds semantic memory integration using Ollama embeddings (nomic-embed-text) for context-aware learning retrieval in Claude Code sessions.
This is an alternative implementation to the existing sentence-transformers approach, using Ollama for fully local embeddings without requiring cloud API keys.
Components Added
src/semantic/src/hooks/semantic-hooks/src/hooks/windows/apps/dashboard/backend/routers/semantic.pydata/seed_heuristics.jsonHow It Works
Test Coverage
Test plan
ollama listsrc/semantic/install.shsrc/semantic/start-daemon.shcurl http://localhost:8888/api/semantic/healthcd src/semantic/tests && ./run_tests.sh~/.claude/hooks/and verify memory injection🤖 Generated with Claude Code