Changelog

What's new in takizen.

CoT Feedback System

AI agents can now learn which memory combinations work best in their reasoning processes. Memories are ranked by effectiveness over time, not just semantic similarity.

Added
  • cot_feedback tool — record which memories were useful in a Chain of Thought session, with an effectiveness score (0–1) and optional notes
  • recall now accepts boost_by_cot and cot_boost_weight — prioritize memories with a proven effectiveness history
  • New Supabase tables: cot_sessions, cot_session_memories, cot_feedback
  • RPC functions: match_memories_cot_boosted, decay_cot_feedback, get_cot_memory_score
  • CoT decay at 0.02/day — more stable than memory decay, runs in the daily 2am cron
Frontend
  • Landing page redesigned — dark-first palette, Supabase-inspired nav with beta badge
  • Bento grid with 6 animated SVG feature cards (semantic memory, instant recall, strength decay, MCP native, memory graph, namespace isolation)
  • /docs — full MCP API reference
  • /dashboard — rebuilt as structured table layout (Vercel/Cloudflare style) with overview-first stats, usage chart, and compact 7-column memory table
  • 404 page and /health endpoint

Compliance & Security

Legal infrastructure for GDPR compliance. All data operations are now auditable, consent is versioned, and users can submit deletion requests with a 30-day deadline.

Added
  • audit_log — append-only record of all operations (SQL rules block UPDATE/DELETE). Satisfies GDPR Art. 30
  • tos_acceptances — versioned ToS consent history per namespace. GDPR Art. 7
  • gdpr_requests — data subject requests (erasure, access, portability) with 30-day deadline tracking. GDPR Art. 12/15/16/17
  • key_prefix on API keys — first 10 chars stored in plaintext for visual identification without exposing the secret
  • stats tool — namespace usage counters (remember/recall this month, recalls today)
  • Monthly rate limit on remember, configurable per plan
Changed
  • RLS enabled on all tables — deny_all for anon and authenticated roles. Only service_role can access from the Worker
  • namespaces.api_key_hash removed — API keys now live exclusively in the api_keys table

Memory Graph

Memories are no longer isolated vectors — they form a graph. Related memories are linked automatically and surfaced together during recall via hybrid search.

Added
  • link tool — create, delete, or list typed relationships between memories. Types: related_to, supports, contradicts, part_of, caused_by
  • Auto-linking on remember — finds similar memories (threshold 0.75, max 5 links) and links them automatically. Best-effort: errors don't fail the operation
  • Graph expansion in recall — results include neighbor memories from the link graph
  • Hybrid search with Reciprocal Rank Fusion (RRF) — combines semantic similarity and graph traversal
  • update tool — modify content and/or tags of an existing memory
  • memory_links table with HNSW index
  • Full-text search — auto-generated fts tsvector column on memories

Initial Release

Core MCP server with four tools, semantic deduplication, automatic decay, and weekly consolidation.

Added
  • remember — store a memory with content, optional tags, and a 1536-dim vector embedding. Semantic deduplication at 0.92 similarity (updates instead of duplicating)
  • recall — semantic search with optional tag filters
  • forget — archive to KV cold storage before deleting from Postgres
  • list — paginated list of namespace memories
  • Auth — SHA-256 hashed API keys, validated on every endpoint except /health
  • Daily decay cron (2am) — reduces strength of inactive memories; archives at 0
  • Weekly consolidation cron (Sunday 3am) — clusters similar memories using claude-haiku (Pro plan)
  • HTTP/SSE transport via @modelcontextprotocol/sdk
Stack
  • Cloudflare Workers (TypeScript runtime)
  • Supabase PostgreSQL + pgvector (VECTOR 1536, HNSW index)
  • OpenRouter — openai/text-embedding-3-small for embeddings, anthropic/claude-haiku-4-5 for consolidation
  • Cloudflare KV for archived memory cold storage
🚀 Launch in seconds

Ready to give your AI
a persistent memory?

Join thousands of developers building smarter agents with takizen.

10k+ Agents connected
2M+ Memories stored
<10ms Avg. latency