# AI use cases for Tencent DB Agent Memory (TencentCloud/TencentDB-Agent-Memory) Repo: [TencentCloud/TencentDB-Agent-Memory](https://github.com/TencentCloud/TencentDB-Agent-Memory) | Use cases: 5 | Page: https://dedupedai.com/use-cases/tencentcloud-tencentdb-agent-memory/ A team-level memory server for AI agents that stores chat memory, skills, wiki pages, and code graphs, and shares them across agents and frameworks. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Give Claude Code and Codex one shared memory server: https://dedupedai.com/use-cases/tencentcloud-tencentdb-agent-memory/shared-memory-for-claude-code-and-codex/ - Index an existing repo so agents check impact before editing: https://dedupedai.com/use-cases/tencentcloud-tencentdb-agent-memory/load-an-existing-codebase-into-codegraph/ - Turn product docs into a wiki that all dev agents can read: https://dedupedai.com/use-cases/tencentcloud-tencentdb-agent-memory/turn-product-docs-into-a-shared-wiki/ - Move existing v1 or v2 memory data into a v3 install: https://dedupedai.com/use-cases/tencentcloud-tencentdb-agent-memory/migrate-v2-data-to-v3/ - Save a release checklist as a Skill and assign it to a release agent: https://dedupedai.com/use-cases/tencentcloud-tencentdb-agent-memory/package-a-release-skill-for-the-release-agent/ ## How to give Claude Code and Codex one shared memory server with Tencent DB Agent Memory Repo: [TencentCloud/TencentDB-Agent-Memory](https://github.com/TencentCloud/TencentDB-Agent-Memory) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Route two coding agents through one local proxy so they read and write the same memory. **Who it is for:** A developer who uses Claude Code and Codex on the same project and repeats the same project context in each new session. **The problem:** Each agent session starts from zero, so project background has to be explained again and again. **The outcome:** Both agents send traffic through the proxy and draw on the same team memory, with the panel open at localhost:8125 to inspect it. ### Steps 1. Run `git clone https://github.com/TencentCloud/TencentDB-Agent-Memory.git` and then `cd TencentDB-Agent-Memory/deploy/global-images` 2. Run `cp .env.example .env`, then open `.env` and fill in the two sets of LLM parameters (memory group and proxy group) 3. Run `./start-all.sh` and wait for it to finish; it prints a one-liner to paste into Claude 4. Open http://localhost:8125 to confirm the panel loads 5. Follow the Proxy setup for Claude Code or Codex in INSTALL.md by pointing the agent base URL to the Proxy ### Prompt to paste into your agent ```text Using the repo TencentDB-Agent-Memory, start all three services from deploy/global-images with ./start-all.sh after filling .env, then point the base URL of to the Proxy as described in INSTALL.md. Expected output: the panel at http://localhost:8125 loads and one test request from completes through the Proxy. Verify that the request appears in the panel or the service logs. ``` ### Caveat The README says no plugin, hook, or MCP server is needed, but each client needs its exact configuration from INSTALL.md, and the LLM keys in .env must be supplied by you. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/tencentcloud-tencentdb-agent-memory/shared-memory-for-claude-code-and-codex/ ## How to index an existing repo so agents check impact before editing with Tencent DB Agent Memory Repo: [TencentCloud/TencentDB-Agent-Memory](https://github.com/TencentCloud/TencentDB-Agent-Memory) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Import a codebase into CodeGraph so agents can see callers, callees, and impact paths. **Who it is for:** A developer joining or maintaining a large codebase who wants agents to understand what a change might break. **The problem:** Agents tend to edit code based on the local file they see and miss callers and dependent modules elsewhere. **The outcome:** The repo's symbols, files, call relationships, and impact paths are indexed, and agents can run impact analysis before modifying code. ### Steps 1. Start the stack with `./start-all.sh` from deploy/global-images after filling in `.env` 2. Open http://localhost:8125 and create a team in Memory Hub 3. In the Knowledge Workshop, import the existing repository so CodeGraph indexes it 4. Check the processing status and asset metadata until indexing completes 5. Point your agent at the team's CodeGraph before it edits code and ask for callers and impact scope first ### Prompt to paste into your agent ```text Using TencentDB-Agent-Memory, import the repository at into CodeGraph through the panel at http://localhost:8125. Before changing , query CodeGraph for its callers, callees, and impact path, and report the list. Verify that the impact list matches a manual grep of the repo for . ``` ### Caveat The README describes CodeGraph import through the panel but does not document the exact import steps, so check the panel and INSTALL.md for the current flow. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/tencentcloud-tencentdb-agent-memory/load-an-existing-codebase-into-codegraph/ ## How to turn product docs into a wiki that all dev agents can read with Tencent DB Agent Memory Repo: [TencentCloud/TencentDB-Agent-Memory](https://github.com/TencentCloud/TencentDB-Agent-Memory) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Convert design docs and runbooks into linked wiki pages and share them with selected agents. **Who it is for:** A tech lead who keeps architecture notes, specs, and ops runbooks in scattered files and wants every development agent to use them. **The problem:** Agents read file lists from scratch each session and lose time finding the right design doc. **The outcome:** Documents become structured wiki pages with a link graph, shared with the team or assigned to development agents. ### Steps 1. Start the stack with `./start-all.sh` from deploy/global-images and open http://localhost:8125 2. Create a team and add the development agents in Memory Hub 3. In the Knowledge Workshop, import product docs, design specs, and ops runbooks so Wiki generates pages 4. Set the Architecture Wiki visibility to `team` or assign it to specific agents 5. Ask one agent to answer a question using the wiki and confirm the cited page matches the source doc ### Prompt to paste into your agent ```text Using TencentDB-Agent-Memory, import the docs in into Wiki through the panel at http://localhost:8125 and make the resulting architecture page visible to the agents . Expected output: a link-graph page list and one answer from an agent that cites a wiki page. Verify that the cited page exists in the panel. ``` ### Caveat Visibility options are private, team, restricted, and agent, and the README does not say how many documents Wiki can process at once. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/tencentcloud-tencentdb-agent-memory/turn-product-docs-into-a-shared-wiki/ ## How to move existing v1 or v2 memory data into a v3 install with Tencent DB Agent Memory Repo: [TencentCloud/TencentDB-Agent-Memory](https://github.com/TencentCloud/TencentDB-Agent-Memory) | Difficulty: Advanced | Time: 60 minutes | Basis: From the README Use the official migration tool to bring older memory data into the current release. **Who it is for:** A user already running an older TencentDB Agent Memory release who wants to keep their stored memory after upgrading. **The problem:** Existing chat memory and assets from older versions would be lost or unused in a fresh v3 install. **The outcome:** Older data is migrated into the v2.0.0 or later storage format, using the flags described in the migration README. ### Steps 1. Read the full usage and flags in MemoryCore/scripts/migrate-v2-to-v3/README.md 2. Change into the MemoryCore/scripts/migrate-v2-to-v3 directory from the repo root (inferred, check the README) 3. Run the migration script with the flags listed in that README against your existing data (inferred, check the README) 4. Start the stack with `./start-all.sh` from deploy/global-images and open http://localhost:8125 5. Check in the panel that migrated Chat Memory and assets appear ### Prompt to paste into your agent ```text Using the repo TencentDB-Agent-Memory, read MemoryCore/scripts/migrate-v2-to-v3/README.md and run the migration for my existing with the flags it lists. Expected output: a migration summary from the script. Verify that the migrated items appear in the panel at http://localhost:8125. ``` ### Caveat The README says new installations can skip migration, and the exact script command and flags are only in the migration README, so take a backup before running it. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/tencentcloud-tencentdb-agent-memory/migrate-v2-data-to-v3/ ## How to save a release checklist as a Skill and assign it to a release agent with Tencent DB Agent Memory Repo: [TencentCloud/TencentDB-Agent-Memory](https://github.com/TencentCloud/TencentDB-Agent-Memory) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Capture a finished release workflow as a reusable skill and equip one agent with it. **Who it is for:** A small team lead who wants the release process learned once to be reused by a dedicated release agent. **The problem:** Release steps live in one person's head or old chat logs, so each release starts from scratch. **The outcome:** A versioned Skill with execution steps and validation rules is shared with the team and bound to the Release agent. ### Steps 1. Start the stack with `./start-all.sh` from deploy/global-images and open http://localhost:8125 2. Import the past conversation session where the release was completed so Skills are extracted 3. Review the extracted Release Checklist Skill and check its execution steps and validation rules 4. Share the Skill with the team and bind it to the Release agent in Agent Loadout 5. Ask the Release agent to run the checklist on a test branch and confirm each step is reported ### Prompt to paste into your agent ```text Using TencentDB-Agent-Memory, extract a Release Checklist Skill from the session and bind it to the agent through the panel at http://localhost:8125. Expected output: the Skill's version, steps, and validation rules, then a checklist run by the agent. Verify the Skill status is shared with the team before it is bound. ``` ### Caveat Skills are private by default, so the Skill must be explicitly shared with the team before the Release agent can use it. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/tencentcloud-tencentdb-agent-memory/package-a-release-skill-for-the-release-agent/