Tencent Open-Sources Agent Memory: Cross-Session Recall with 61% Fewer Tokens
dr_cintas · x · 2026-08-01
Tencent has open-sourced TencentDB Agent Memory, a self-hostable, team-level memory hub for AI agents that retains memory across sessions.
- Core features: Transforms conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) with governed sharing and ACLs across agents and frameworks.
- Performance: Replaces opaque vector piles, cutting token usage by 61% and boosting PersonaMem accuracy from 48% to 76%.
Related event: Tencent Open-Sources Agent Memory Framework, Cutting Token Usage by 61%(3 posts)→
More from coding & agent
- 'LLM code is sloppy' rebutted with real ffmpeg code: identical if/else branches in a top library — kingslyj · 2026-10-16
- Office-editing tool calls need file, worktree and unit: lessons from dsh-univer-office — FunDistribution6537 · 2026-10-16
- Architect MD workflow: Gemini one-shot outputs that beat Opus, via 5-lens plan critique — oikk01 · 2026-10-16
- Prove a coding agent actually ran the tests: check artifacts, not approvals — ComprehensiveShake76 · 2026-10-16
- Building an acceptance harness for AI spreadsheet edits: allowlists, recalc checks, idempotency — ukdicha-modakkk · 2026-10-16
- Agent actions need checks outside the model: NVIDIA demos lean on guardrails amid wave of real agent incidents — Creamy-And-Crowded · 2026-10-16