Tencent/TencentDB-Agent-Memory
TencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.
Repository profile
Hindsight: Agent Memory That Learns
Repository updates
Get generated vectorize-io/hindsight development summaries by email, or follow the weekly and monthly RSS feeds.
Sign in to subscribe by email. RSS feeds are public.
Sign in to subscribeTracked growth, recent movement, and commit velocity from stored repository snapshots.
Latest capture 2026-07-13 03:08
5 captures since 2026-05-23
Stars from baseline +4009
All tracked data
Frameworks, package managers, ecosystems, and dependency manifests found during catalog scans.
Scanned 2026-07-13 03:08
package.json
javascript ecosystem,
0 dependencies
pyproject.toml
python ecosystem,
0 dependencies
package-lock.json
javascript ecosystem,
0 dependencies
uv.lock
python ecosystem,
0 dependencies
hindsight-all-npm/package.json
javascript ecosystem,
4 dependencies
hindsight-all-slim/pyproject.toml
python ecosystem,
6 dependencies
hindsight-all/pyproject.toml
python ecosystem,
6 dependencies
hindsight-api-slim/pyproject.toml
python ecosystem,
78 dependencies
Searchable topics, generated tags, and stack labels that explain where this repository fits.
Agent instructions and tool configuration paths found in the repository tree.
AI agent config detected
Key config paths
1 more config path detected.
Nearest indexed repositories by embedding similarity.
TencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
Memory system for autonomous agents - built by an agent, for agents
Agent Skills as a Memory Layer
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
Auditable workspaces for AI coding agents: sandboxed worktrees, conflict-free multi-agent orchestra, 95% lower token waste, and persistent memory.