memorix 1.4.4 → 1.4.6

package/docs/1.4.5-AGENT-AUTO-MEMORY-RESEARCH.md

@@ -0,0 +1,95 @@
+# Research: Claude Code Auto Memory and What Memorix Should Borrow
+
+> Status: research note (2026-08-14, against the 1.4.5 line). This document
+> records findings and direction; it is not a shipped feature and not a claim
+> that any item below is implemented.
+
+## Question
+
+Claude Code's Auto Memory gives a single agent a file-based, recallable
+workspace memory: `~/.claude/projects/<git-root>/memory/` with a `MEMORY.md`
+entrypoint index and typed memory files. What is the design, how does it
+compare with Memorix, and which parts are worth absorbing?
+
+## Sourcing caveat
+
+The mechanism-level details below come from community source-level analyses
+and third-party write-ups, not from an official Anthropic specification:
+
+- Source-level analysis of the memory system (`memdir`): project-memory.mdx
+  in a community Claude Code docs mirror
+  (https://github.com/claude-code-best/claude-code/blob/master/docs/context/project-memory.mdx)
+- Independent critical analysis:
+  https://dev.to/chen_zhang_bac430bc7f6b95/claude-codes-memory-4-layers-of-complexity-still-just-grep-and-a-200-line-cap-2kn9
+- Community adoption discussion:
+  https://developer.aliyun.com/article/1713756
+
+Treat feature-flag names (`KAIROS`, `TEAMMEM`) and thresholds as observed
+behavior of a moving target, not as stable contracts.
+
+## The design, in brief
+
+- Pure Markdown files, no database, no vector store. One directory per
+  sanitized Git root, shared across worktrees of that repository.
+- `MEMORY.md` is the entrypoint index: at most 200 lines AND 25 KB, one
+  `- [Title](file.md) — one-line hook` pointer per line, loaded into every
+  session. The knowledge lives in topic files, loaded on demand.
+- A closed four-type taxonomy (user / feedback / project / reference), each
+  type with explicit `<when_to_save>`, `<how_to_use>`, and `<body_structure>`
+  rules. Each memory file carries frontmatter whose `description` field is
+  written for the recall system, not for humans.
+- The core saving rule: only store information that cannot be derived from
+  the current project state. Code, file paths, and Git history are
+  re-derivable and do not belong in memory.
+- Recall is a lightweight model side-query that picks at most 5 relevant
+  memories from the manifest, with denoising for recently used tools and
+  dedup of already-surfaced files.
+- Memory is injected as a user-context message (prompt-cache friendly).
+- Drift defense is prompt-level: a memory that names a file, function, or
+  flag is a claim about the past — verify before recommending. An explicit
+  "ignore memory" instruction means proceed as if `MEMORY.md` were empty.
+- Consolidation ("dream") is time/volume-triggered, merging contradictions
+  and pruning stale entries. Long-running sessions may switch to append-only
+  daily logs that a later pass distills.
+- Security: the memory directory resolves only from user-level input
+  (environment override or a user setting). Project-level settings are
+  deliberately excluded from that resolution chain, so a hostile repository
+  cannot redirect memory storage to arbitrary paths.
+
+## Comparison with Memorix
+
+| Aspect | Claude Code Auto Memory | Memorix (1.4.5) |
+| --- | --- | --- |
+| Audience | One agent, one product | Any MCP/CLI/SDK/hooks agent, shared |
+| Storage | Markdown files | SQLite canonical store + Orama search |
+| Entry injection | Full index, fixed 200-line/25 KB cap | Task-lensed Workset, budget-governed |
+| Taxonomy | Closed 4 types | 11 observation types + reasoning + Git + long-term |
+| Recall | Paid model side-query (needs a key) | Local BM25 primary + bounded semantic fallback |
+| Drift defense | Prompt-level verify-before-use | Freshness, attribution guard, evidence governor |
+| Cleanup | Time/volume-triggered consolidation | Retention + dedup + consolidation pipeline |
+| Path security | User-level-only resolution | User-level-only by construction (env var only) |
+
+The critical review's complaint — memory trapped in one product's sandbox,
+no cross-agent sharing — is exactly the space Memorix occupies.
+
+## What Memorix should borrow (directions, not commitments)
+
+Shipped (2026-08-14, continuing on the 1.4.x line):
+1. **The "only store the underivable" rule, made explicit.** Now part of every
+   generated guidance file, with the dual-channel rule and the verify-before-use
+   / ignore semantics.
+2. **Dual-channel feedback.** Guidance now tells agents to record validated
+   approaches and explicit user confirmations, not only corrections.
+3. **Session-level dedup of already-surfaced memory.** `memorix_search`
+   demotes rows already shown in the same session (never removes them) and
+   remembers the surfaced set per session; measured 25% → 19% duplicate rate
+   with hits and budget unchanged.
+4. **Explicit ignore semantics.** Guidance now states the contract: an ignore
+   instruction means proceed as if memory were empty.
+5. **Keep the security boundary tested.** Pinned by
+   `tests/config/data-dir-boundary.test.ts`.
+
+Scoring lives in `tests/evaluation/session-replay-evaluation.test.ts`
+(retrieval) and `tests/evaluation/guidance-content.test.ts` (guidance); both
+are deterministic and offline. A future change to these behaviors must update
+the pinned scores only with a measured improvement.

package/docs/AGENT_OPERATOR_PLAYBOOK.md

@@ -23,7 +23,7 @@ It supports:
 - HTTP MCP service + dashboard (`memorix background start` or `memorix serve-http --port 3211`)
 - bundled terminal agent (`memorix` or `memcode`) that uses the same shared memory pool
 - local-first project-scoped memory
-- cross-agent recall across Cursor, Claude Code, Codex, CodeBuddy Code, Windsurf, Gemini CLI, GitHub Copilot, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, and Trae
+- cross-agent recall across Cursor, Claude Code, Codex, CodeBuddy Code, Windsurf, Gemini CLI, GitHub Copilot, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, and DeepSeek Harness
 
 ### Current 1.4 Baseline
 
@@ -41,7 +41,7 @@ For the 1.4 release line, the visible product shape is:
 - `memorix_project_context` / `memorix context "..."` is the normal black-box entry for non-trivial coding work: it assembles a bounded task Workset instead of injecting a generic memory dump; `memorix resume "..."` is the explicit CLI continuation projection
 - Code State keeps local snapshots and freshness links; a healthy pre-existing local CodeGraph index can add a bounded semantic outline, but Memorix never initializes or synchronizes that external index itself
 - `memorix knowledge` is an explicit review path for source-backed Markdown knowledge and canonical workflows. Do not initialize a versioned workspace or apply a proposal unless the user asks for that managed artifact
-- integration surfaces are agent-specific: Claude Code, Codex, GitHub Copilot CLI, Antigravity, and Hermes receive plugin packages; OpenClaw receives a compatible bundle; Pi and Oh-my-Pi receive package entries; Gemini CLI receives an extension package; OpenCode receives a plugin file and skill; Cursor and other agents receive MCP/rules/hooks where supported
+- integration surfaces are agent-specific: Claude Code, Codex, GitHub Copilot CLI, Antigravity, and Hermes receive plugin packages; OpenClaw receives a compatible bundle; Pi and Oh-my-Pi receive package entries; Gemini CLI receives an extension package; OpenCode receives a plugin file and skill; DeepSeek Harness receives an MCP patch row, AGENTS.md guidance, and skills; Cursor and other agents receive MCP/rules/hooks where supported
 - privacy-safe diagnostics and receipts avoid raw chat, memory text, query text, tool payloads, and local file paths
 
 ---
@@ -256,6 +256,7 @@ What this installs depends on the target agent:
 - Hermes Agent: Hermes plugin under Hermes home (`%LOCALAPPDATA%\hermes` on native Windows, `~/.hermes` elsewhere, or `HERMES_HOME`), enabled in `config.yaml`, with plugin hooks, slash command, CLI command, skills, and MCP config.
 - Oh-my-Pi: `omp.extensions` package linked through `omp plugin link <path>` when available, with extension hook events, a `memorix` command, skills, and MCP config.
 - Windsurf, Kiro, Trae: MCP config plus rules/hooks where supported.
+- DeepSeek Harness: a Memorix `@deepseek-ai/dsh-mcp-client` row in `$DSH_HOME/cordis.patch.yml` (default `~/.dsh/cordis.patch.yml`), harness `AGENTS.md` guidance, and official skills under `$DSH_HOME/skills`. Tools appear as `mcp__memorix__*`; there is no hooks surface. Project-local setup writes project `AGENTS.md` guidance and `.dsh/skills`, while the MCP row stays in the harness-level patch file.
 
 Run the same setup command without `--global` only when you intentionally want repo-local guidance, rules, or hooks for a single Git project.
 

package/docs/API_REFERENCE.md

@@ -223,7 +223,7 @@ Important inputs:
 - optional `relatedCommits`
 - optional `relatedEntities`
 - optional `visibility`: `project` (default), `personal`, or `team`
-- optional `longTerm`: an explicit source-backed long-term candidate with `kind` (`episodic`, `semantic`, or `procedural`), an optional `scope` (`project`, `user`, or `team`), tags, and applicability
+- optional `longTerm`: an explicit source-backed long-term record with `kind` (`episodic`, `semantic`, or `procedural`), an optional `scope` (`project`, `user`, or `team`), tags, and applicability
 
 Visibility controls who can retrieve a record through agent-facing memory
 tools. Normal memories default to `project`. `personal` and `team` writes
@@ -236,11 +236,15 @@ files, `memorix_store` returns without writing. Use `overrideReadOnly: true`
 only when the user explicitly asks to preserve a record during that task.
 
 `longTerm` is deliberately opt-in. It stores the normal Observation first, then
-creates a separate candidate with an evidence reference. Candidates are not
-inserted into a Task Workset. Review them with `memorix memory long-term
-list|show|qualify|approve|archive|supersede`. Source-derived entries remain
+creates a separate record with an evidence reference. Because an explicit
+request carries its own source evidence, the new record is auto-qualified on
+the spot and enters Task Worksets as durable context; approval remains an
+explicit operator review. Manage records with `memorix memory long-term
+list|show|approve|archive|supersede`. Source-derived entries remain
 project-bound; only a manual or user-confirmed `user + portable` record created
 through the CLI may cross local projects for the same local installation.
+Hook-captured and git-derived candidates stay in the candidate state until
+qualified.
 
 Example:
 
@@ -540,6 +544,21 @@ Use it to inspect:
 - stage timing
 - recent pipeline behavior
 
+### `memorix_audit_project`
+
+Scan the current project for observations that may have been written to the
+wrong project bucket — entities that appear exclusively in a different
+project. Read-only; nothing is changed.
+
+Available in the `full` tool profile (`MEMORIX_MODE=full` or `--mode full`).
+
+Important inputs:
+
+- optional `threshold` — minimum occurrences in another project to flag
+  (default: 2)
+
+Archive confirmed mis-attributed observations with `memorix_resolve`.
+
 ---
 
 ## 7. Skills and Promotion Tools

package/docs/CONFIGURATION.md

@@ -294,10 +294,24 @@ Server and dashboard behavior.
 
 Common keys:
 
-- `transport = "stdio"`
-- `port = 3211`
+- `transport = "stdio"` — advisory. An explicit `memorix serve-http` still
+  runs on HTTP and prints a notice; this key documents the intended mode.
+- `port = 3211` — default listener port for `memorix serve-http` when
+  `--port` is not given.
 - `dashboard = true`
-- `dashboard_port = 3210`
+- `dashboard_port = 3210` — default port for `memorix dashboard` when
+  `--port` is not given.
+
+### Reserved sections (parsed, not yet enforced)
+
+These sections exist so future releases do not need a config format change.
+Today no runtime behavior reads them; set them only as forward-looking notes.
+
+- `[team]` (`enabled`, `workspace_collection`) — coordination defaults.
+- `[hooks]` (`native_memcode`, `external_agents`) — hook bootstrap policy.
+- The former `mcpServers` key in `memorix.yml` was removed: no code ever
+  consumed it, and Memorix is not an MCP aggregator. Unknown keys are
+  ignored, so old files keep loading.
 
 ---
 

package/docs/INTEGRATIONS.md

@@ -20,7 +20,7 @@ That command installs the recommended Memorix package or config for the target a
 | Package or extension | Bundles Memorix for agents that use package or extension systems | `memorix setup --agent pi --global`, `omp --global`, or `gemini-cli --global` |
 | Local plugin | Installs a local plugin file where the agent loads plugins directly | `memorix setup --agent opencode --global` |
 | MCP server | Gives an agent live tools for search, recall, storage, reasoning, and coordination | bundled by setup, host MCP config, or `memorix serve` |
-| Usage guidance | Tells the agent when and how to use memory | `CLAUDE.md`, `AGENTS.md`, `GEMINI.md`, Cursor/Windsurf/Kiro/Trae rules |
+| Usage guidance | Tells the agent when and how to use memory | `CLAUDE.md`, `AGENTS.md`, `GEMINI.md`, Cursor/Windsurf/Kiro/Trae rules, DeepSeek Harness AGENTS.md |
 | Hooks | Captures useful session events when the agent exposes hook events | bundled by plugin packages or generated hook files |
 | Skills | Turns durable project knowledge into reusable task guidance | plugin skills, `memorix skills`, `memorix_promote` |
 | memcode | Opens a terminal coding agent that already uses Memorix memory | `memorix`, `memcode` |
@@ -36,7 +36,7 @@ CLI, MCP, and HTTP have separate jobs:
 
 Generated guidance also has scope:
 
-- Project guidance (`CLAUDE.md`, `AGENTS.md`, `GEMINI.md`, Cursor/Windsurf/Kiro/Trae rules) may say the repository is configured for Memorix.
+- Project guidance (`CLAUDE.md`, `AGENTS.md`, `GEMINI.md`, Cursor/Windsurf/Kiro/Trae rules, DeepSeek Harness AGENTS.md) may say the repository is configured for Memorix.
 - Plugin or skill package guidance is workspace-safe. It says to use Memorix when the active workspace has Memorix tools available.
 - `--global` writes user-level plugin, config, and hook surfaces where the host supports them.
 - Running the same setup command without `--global` is the repo-local path for one project only.
@@ -63,6 +63,7 @@ Generated guidance also has scope:
 | Kiro | `memorix setup --agent kiro --global` | Kiro MCP/steering/hooks config | MCP config, `.kiro/steering/memorix.md`, `.kiro/hooks/*.kiro.hook` | Uses Kiro steering and hook files. |
 | Antigravity | `memorix setup --agent antigravity --global` | Antigravity plugin | Plugin under `~/.gemini/config/plugins/memorix` or `.agents/plugins/memorix`, with `plugin.json`, `mcp_config.json`, `hooks.json`, rules, and skills | Uses Antigravity's official plugin layout. Dedicated MCP configs live at `~/.gemini/config/mcp_config.json` or `.agents/mcp_config.json`; legacy Gemini settings are read only for compatibility. |
 | Trae | `memorix setup --agent trae --global` | Trae MCP/rules config | MCP config and `.trae/rules/project_rules.md` | Current support is MCP plus project rules. |
+| DeepSeek Harness | `memorix setup --agent dsh --global` | DeepSeek Harness MCP patch | Memorix `@deepseek-ai/dsh-mcp-client` row in `$DSH_HOME/cordis.patch.yml` (default `~/.dsh/cordis.patch.yml`), guidance in the harness `AGENTS.md`, and official skills under `$DSH_HOME/skills` | Tools appear as `mcp__memorix__*`. No hooks surface. Project-local setup writes project `AGENTS.md` guidance and `.dsh/skills`; the MCP row always lives in the harness-level patch file. |
 | memcode | `memorix` or `memcode` | Bundled terminal agent | Built-in Memorix memory access | memcode uses the same project memory pool; it is not a separate memory silo. |
 | Any MCP client | Manual MCP config | MCP stdio or HTTP | `memorix serve` or `memorix background start` | Use stdio first unless you need a shared HTTP endpoint. |
 
@@ -87,9 +88,15 @@ memorix setup --agent cursor --global
 memorix setup --agent pi --global
 memorix setup --agent gemini-cli --global
 memorix setup --agent opencode --global
+memorix setup --agent windsurf --global
+memorix setup --agent kiro --global
+memorix setup --agent antigravity --global
+memorix setup --agent trae --global
 memorix setup --agent openclaw --global
 memorix setup --agent hermes --global
+memorix setup --agent codebuddy --global
 memorix setup --agent omp --global
+memorix setup --agent dsh --global
 ```
 
 Use `memorix setup --agent all --global` only when you intentionally want every supported agent integration generated for the current machine/user scope.

package/docs/KNOWN_ISSUES_AND_ROADMAP.md

@@ -63,6 +63,7 @@ Memorix 是本地优先、可插拔的 Agent Memory 系统。它给不同 Agent
 
 - 跟进受用户需求推动的集成，例如 [Qwen 自动 hooks](https://github.com/AVIDS2/memorix/issues/3) 与 [持久化 Agent 身份](https://github.com/AVIDS2/memorix/issues/49)；
 - 独立推进记忆能力的实证研究，例如[模型能力如何改变项目记忆收益与伤害边界](https://github.com/AVIDS2/memorix/issues/152)，不把研究假设当作产品已经证明的效果。
+- DeepSeek Harness 支持已随 `memorix setup --agent dsh` 发布：写入 MCP 行（`$DSH_HOME/cordis.patch.yml`，默认 `~/.dsh/cordis.patch.yml`）、AGENTS.md 使用规范与官方 skills；工具以 `mcp__memorix__*` 形式出现。
 
 ---
 

package/docs/MEMCODE.md

@@ -224,7 +224,7 @@ memcode update self
 
 Memorix is the shared memory layer. memcode is the bundled terminal agent built on top of it.
 
-Use Memorix when you want Claude Code, Codex, Cursor, Windsurf, Copilot, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Kiro, Antigravity, Trae, or another MCP client to share project memory.
+Use Memorix when you want Claude Code, Codex, Cursor, Windsurf, Copilot, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Kiro, Antigravity, Trae, DeepSeek Harness, or another MCP client to share project memory.
 
 Use memcode when you want a terminal agent that already uses that memory layer.
 

package/docs/SETUP.md

@@ -17,9 +17,9 @@ Common runtime entry points:
 
 | Entry | Use it for |
 | --- | --- |
-| `memorix setup --agent <agent> --global` | one-command user-level agent integration |
+| `memorix setup --agent <agent> --global` | one-command user-level agent integration; installs the stdio server with `--mode lite` so every tool taught in the generated guidance is actually reachable |
 | `memorix` CLI commands | direct workflows: setup, search/store, Git Memory, import/export, dashboard, diagnostics, orchestration, and automation |
-| `memorix serve` | stdio MCP server for IDEs and coding agents; defaults to a compact `micro` tool profile |
+| `memorix serve` | stdio MCP server for IDEs and coding agents; defaults to a compact `micro` tool profile when launched manually |
 | `memorix background start` | long-lived HTTP MCP service plus dashboard |
 | `memorix serve-http --port 3211` | foreground HTTP MCP for debugging or supervised launches |
 | `memorix` / `memcode` | bundled terminal agent that uses the same Memorix memory pool |
@@ -68,9 +68,15 @@ memorix setup --agent cursor --global
 memorix setup --agent pi --global
 memorix setup --agent gemini-cli --global
 memorix setup --agent opencode --global
+memorix setup --agent windsurf --global
+memorix setup --agent kiro --global
+memorix setup --agent antigravity --global
+memorix setup --agent trae --global
 memorix setup --agent openclaw --global
 memorix setup --agent hermes --global
+memorix setup --agent codebuddy --global
 memorix setup --agent omp --global
+memorix setup --agent dsh --global
 ```
 
 What this does:
@@ -86,6 +92,7 @@ What this does:
 - OpenClaw: installs `~/.openclaw/extensions/memorix` as an OpenClaw-compatible bundle with bundled stdio MCP, skills, and an OpenClaw `HOOK.md`/`handler.ts` hook pack.
 - Hermes Agent: installs into Hermes home (`%LOCALAPPDATA%\hermes` on native Windows, `~/.hermes` elsewhere, or `HERMES_HOME`), enables it in `config.yaml`, registers plugin hooks, a slash command, a CLI command, skills, and writes MCP config in `mcp_servers`.
 - Oh-my-Pi: installs an `omp.extensions` package, links it with `omp plugin link <path>` when available, and writes `.omp/mcp.json` or `~/.omp/agent/mcp.json` for MCP.
+- DeepSeek Harness: writes a Memorix `@deepseek-ai/dsh-mcp-client` row into `$DSH_HOME/cordis.patch.yml` (default `~/.dsh/cordis.patch.yml`), appends guidance to the harness `AGENTS.md` (`$DSH_HOME/AGENTS.md`, default `~/.dsh/AGENTS.md`), and installs official skills under `$DSH_HOME/skills` (default `~/.dsh/skills`). Tools appear as `mcp__memorix__*`; there is no hooks surface. Project-local setup (without `--global`) appends guidance to the project-root `AGENTS.md` and installs skills under `.dsh/skills`, while the MCP row still goes to the harness-level patch file.
 - Other supported agents: writes their MCP/rules/hooks files according to agent support.
 
 Global setup writes user-level plugin, config, and hook files where the host supports them. Use the same command without `--global` only when you explicitly want repo-local guidance, rules, or hooks for the current project.
@@ -117,7 +124,7 @@ memorix doctor agents --agent <agent>
 memorix setup --agent <agent> --global
 ```
 
-Use this for Claude Code, Codex, Cursor, Windsurf, Copilot, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, or any supported agent. It is the default user-facing install path.
+Use this for Claude Code, Codex, Cursor, Windsurf, Copilot, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, DeepSeek Harness, or any supported agent. It is the default user-facing install path.
 
 To see the current setup matrix:
 
@@ -144,7 +151,9 @@ memorix serve
 
 Use this when your agent only needs a raw local stdio MCP process or you are debugging a manual config. The agent starts `memorix serve` and communicates with it over stdio.
 
-The stdio server defaults to `--mode micro`, which exposes 9 high-signal tools so agent context is not crowded by rarely used schemas. Use `memorix serve --mode lite` for the extended solo memory surface, `--mode team` for coordination tools, or `--mode full` for advanced and MCP Memory compatibility tools.
+A bare `memorix serve` defaults to `--mode micro`, which exposes 9 high-signal tools so agent context is not crowded by rarely used schemas. Use `memorix serve --mode lite` for the extended solo memory surface, `--mode team` for coordination tools, or `--mode full` for advanced and MCP Memory compatibility tools.
+
+`memorix setup` writes `--mode lite` into the installed MCP config: the generated guidance teaches the extended surface (sessions, timeline, reasoning, retention), so the installed server must actually expose it. Override with `MEMORIX_MODE` if you prefer a different profile.
 
 Generic stdio MCP config:
 
@@ -666,6 +675,7 @@ Common MCP config locations:
 | Hermes Agent | `%LOCALAPPDATA%\hermes\config.yaml` on native Windows, `~/.hermes/config.yaml` elsewhere, or `HERMES_HOME\config.yaml` |
 | Oh-my-Pi | `.omp/mcp.json` or `~/.omp/agent/mcp.json` |
 | Trae | `%APPDATA%/Trae/User/mcp.json` on Windows |
+| DeepSeek Harness | `$DSH_HOME/cordis.patch.yml` (default `~/.dsh/cordis.patch.yml`) |
 
 ---
 

package/llms-full.txt

@@ -2,7 +2,7 @@
 
 > Local-first shared memory layer for AI coding agents.
 
-Memorix is a TypeScript/Node.js project that gives AI coding agents persistent, project-aware memory. It targets software development workflows, not generic chat. It works across Claude Code, Codex, CodeBuddy Code, Cursor, Windsurf, GitHub Copilot CLI, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, and any agent that can speak MCP over stdio or HTTP. Integrations usually start with `memorix setup --agent <agent> --global`, which installs the recommended user-level package or config for that agent: plugin packages when supported, package or extension entries, MCP config, generated guidance, hooks, skills, or the bundled terminal agent.
+Memorix is a TypeScript/Node.js project that gives AI coding agents persistent, project-aware memory. It targets software development workflows, not generic chat. It works across Claude Code, Codex, CodeBuddy Code, Cursor, Windsurf, GitHub Copilot CLI, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, DeepSeek Harness, and any agent that can speak MCP over stdio or HTTP. Integrations usually start with `memorix setup --agent <agent> --global`, which installs the recommended user-level package or config for that agent: plugin packages when supported, package or extension entries, MCP config, generated guidance, hooks, skills, or the bundled terminal agent.
 
 If you are an AI coding agent helping a user install, operate, or troubleshoot Memorix, read `docs/AGENT_OPERATOR_PLAYBOOK.md` before taking action. It is the main reference for install, runtime selection, Git/project binding, MCP integration, hooks, and troubleshooting.
 
@@ -36,6 +36,7 @@ It installs the recommended Memorix integration for the target agent:
 - Gemini CLI: local Gemini extension package with MCP and `GEMINI.md` context.
 - OpenCode: local plugin file, `opencode.json` MCP config, OpenCode skill, and `AGENTS.md` guidance.
 - Windsurf, Kiro, Antigravity, Trae: MCP config plus rules/hooks where supported.
+- DeepSeek Harness: MCP patch row (`$DSH_HOME/cordis.patch.yml`) plus `AGENTS.md` guidance and official skills.
 
 Use:
 
@@ -131,7 +132,7 @@ memorix orchestrate --goal "Add authentication"
 - plugin packages: Claude Code, Codex, and GitHub Copilot CLI
 - package or extension entries: Pi package and Gemini CLI extension package
 - local plugins: OpenCode local plugin file and skill
-- project instructions and rules: AGENTS.md, GEMINI.md, Cursor rules, Windsurf rules, Kiro steering, Trae rules
+- project instructions and rules: AGENTS.md, GEMINI.md, Cursor rules, Windsurf rules, Kiro steering, Trae rules, DeepSeek Harness AGENTS.md
 - hooks: agent event capture routed through `memorix hook`
 - skills: durable project knowledge promoted into reusable task guidance
 
@@ -365,7 +366,7 @@ Docker is for the HTTP service. The container must have access to the repositori
 
 ## Supported Clients
 
-Memorix supports Claude Code, Codex, CodeBuddy Code, Cursor, Windsurf, GitHub Copilot CLI, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, memcode, and other stdio or HTTP MCP clients.
+Memorix supports Claude Code, Codex, CodeBuddy Code, Cursor, Windsurf, GitHub Copilot CLI, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, DeepSeek Harness, memcode, and other stdio or HTTP MCP clients.
 
 Support depth differs by client:
 
@@ -374,7 +375,7 @@ Support depth differs by client:
 - Claude Code, Codex, and GitHub Copilot CLI receive local plugin packages.
 - Pi receives a user-level package when setup runs with `--global`; Gemini CLI receives a local extension package.
 - OpenClaw receives a compatible bundle; Hermes Agent receives a plugin package; Oh-my-Pi receives a package/extension entry.
-- Project instructions and rules include AGENTS.md, GEMINI.md, Cursor rules, Windsurf rules, Kiro steering, and Trae rules.
+- Project instructions and rules include AGENTS.md, GEMINI.md, Cursor rules, Windsurf rules, Kiro steering, Trae rules, and DeepSeek Harness AGENTS.md.
 - Hooks are generated for agents that expose usable hook events.
 - OpenCode receives a local plugin file at `.opencode/plugins/memorix.js`, an OpenCode skill at `.opencode/skills/memorix-memory/SKILL.md`, plus `opencode.json` MCP config.
 - memcode is the bundled terminal agent and uses the same project memory pool.

package/llms.txt

@@ -2,7 +2,7 @@
 
 > Local-first shared memory layer for AI coding agents.
 
-Memorix gives coding agents persistent, project-aware memory across sessions, IDEs, terminals, and MCP clients. It stores project knowledge once so multiple agents can retrieve it through plugin packages, MCP, CLI, SDK, generated rules/instructions, hooks, skills, local plugins, or the bundled terminal agent. It works with Claude Code, Codex, CodeBuddy Code, Cursor, Windsurf, GitHub Copilot CLI, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, and other MCP-capable agents.
+Memorix gives coding agents persistent, project-aware memory across sessions, IDEs, terminals, and MCP clients. It stores project knowledge once so multiple agents can retrieve it through plugin packages, MCP, CLI, SDK, generated rules/instructions, hooks, skills, local plugins, or the bundled terminal agent. It works with Claude Code, Codex, CodeBuddy Code, Cursor, Windsurf, GitHub Copilot CLI, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Kiro, Antigravity, Trae, DeepSeek Harness, and other MCP-capable agents.
 
 ## Entry Points
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "memorix",
   "mcpName": "io.github.AVIDS2/memorix",
-  "version": "1.4.4",
+  "version": "1.4.6",
   "description": "Local-first shared memory layer for AI coding agents across MCP clients, Git history, reasoning context, and project sessions.",
   "type": "module",
   "sideEffects": false,

package/plugins/antigravity/memorix/mcp_config.json

@@ -3,7 +3,9 @@
     "memorix": {
       "command": "memorix",
       "args": [
-        "serve"
+        "serve",
+        "--mode",
+        "lite"
       ]
     }
   }

package/plugins/claude/memorix/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://anthropic.com/claude-code/plugin.schema.json",
   "name": "memorix",
-  "version": "1.4.4",
+  "version": "1.4.6",
   "description": "Shared workspace memory for Claude Code and other AI coding agents.",
   "author": {
     "name": "AVIDS2",

package/plugins/claude/memorix/.mcp.json

@@ -2,7 +2,7 @@
   "mcpServers": {
     "memorix": {
       "command": "memorix",
-      "args": ["serve"],
+      "args": ["serve", "--mode", "lite"],
       "alwaysLoad": true
     }
   }

package/plugins/codebuddy/memorix/.codebuddy-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "memorix",
-  "version": "1.4.4",
+  "version": "1.4.6",
   "description": "Local-first project memory for CodeBuddy Code and other coding agents.",
   "author": {
     "name": "AVIDS2",

package/plugins/codebuddy/memorix/.mcp.json

@@ -3,7 +3,7 @@
     "memorix": {
       "type": "stdio",
       "command": "memorix",
-      "args": ["serve"]
+      "args": ["serve", "--mode", "lite"]
     }
   }
 }

package/plugins/codex/memorix/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "memorix",
-  "version": "1.4.4",
+  "version": "1.4.6",
   "description": "Shared workspace memory for Codex and other AI coding agents.",
   "author": {
     "name": "AVIDS2",

package/plugins/codex/memorix/.mcp.json

@@ -2,7 +2,7 @@
   "mcpServers": {
     "memorix": {
       "command": "memorix",
-      "args": ["serve"]
+      "args": ["serve", "--mode", "lite"]
     }
   }
 }

package/plugins/copilot/memorix/.mcp.json

@@ -2,7 +2,7 @@
   "mcpServers": {
     "memorix": {
       "command": "memorix",
-      "args": ["serve"]
+      "args": ["serve", "--mode", "lite"]
     }
   }
 }

package/plugins/copilot/memorix/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "memorix",
-  "version": "1.4.4",
+  "version": "1.4.6",
   "description": "Shared local workspace memory for GitHub Copilot CLI and other AI coding agents.",
   "author": {
     "name": "AVIDS2",

package/plugins/gemini/memorix/gemini-extension.json

@@ -1,11 +1,13 @@
 {
   "name": "memorix",
-  "version": "1.4.4",
+  "version": "1.4.6",
   "mcpServers": {
     "memorix": {
       "command": "memorix",
       "args": [
-        "serve"
+        "serve",
+        "--mode",
+        "lite"
       ]
     }
   },

package/plugins/omp/memorix/package.json

@@ -1,6 +1,6 @@
 {
   "name": "memorix-omp-package",
-  "version": "1.4.4",
+  "version": "1.4.6",
   "description": "Memorix shared workspace memory package for Oh-my-Pi.",
   "license": "Apache-2.0",
   "keywords": [

package/plugins/openclaw/memorix/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "memorix",
-  "version": "1.4.4",
+  "version": "1.4.6",
   "description": "Shared workspace memory for OpenClaw and other AI coding agents.",
   "author": {
     "name": "AVIDS2",

package/plugins/openclaw/memorix/.mcp.json

@@ -3,7 +3,9 @@
     "memorix": {
       "command": "memorix",
       "args": [
-        "serve"
+        "serve",
+        "--mode",
+        "lite"
       ]
     }
   }

package/plugins/pi/memorix/package.json

@@ -1,6 +1,6 @@
 {
   "name": "memorix-pi-package",
-  "version": "1.4.4",
+  "version": "1.4.6",
   "description": "Memorix shared workspace memory package for Pi coding agent.",
   "license": "Apache-2.0",
   "keywords": [

package/server.json

@@ -7,7 +7,7 @@
     "url": "https://github.com/AVIDS2/memorix",
     "source": "github"
   },
-  "version": "1.4.4",
+  "version": "1.4.6",
   "websiteUrl": "https://github.com/AVIDS2/memorix#readme",
   "icons": [
     {
@@ -22,7 +22,7 @@
     {
       "registryType": "npm",
       "identifier": "memorix",
-      "version": "1.4.4",
+      "version": "1.4.6",
       "runtimeHint": "npx",
       "packageArguments": [
         {

package/src/cli/commands/agent-integrations.ts

@@ -124,6 +124,7 @@ const GUIDANCE_AGENTS = new Set<AgentName>([
   'kiro',
   'opencode',
   'trae',
+  'dsh',
 ]);
 
 const CODEX_PLUGIN_NAME = 'memorix';
@@ -787,7 +788,12 @@ async function inspectMcp(agent: AgentName, projectRoot: string, scope: AgentInt
     }
 
     const configPath = adapter.getConfigPath(targetScope === 'project' ? projectRoot : undefined);
-    if (targetScope === 'global' && configPath === adapter.getConfigPath(projectRoot)) continue;
+    if (targetScope === 'global' && configPath === adapter.getConfigPath(projectRoot) && scope === 'all') {
+      // User-level-only adapters (Trae, DSH) resolve one path for every
+      // scope. Deduplicate only when the project iteration also runs;
+      // an explicit global-only scope must still inspect the shared path.
+      continue;
+    }
 
     if (!existsSync(configPath)) {
       checks.push({

package/src/cli/commands/dashboard.ts

@@ -22,8 +22,8 @@ export default defineCommand({
     args: {
         port: {
             type: 'string',
-            description: 'Port to run the dashboard on (default: 3210)',
-            default: '3210',
+            description: 'Port to run the dashboard on (default: [server].dashboardPort or 3210)',
+            required: false,
         },
     },
     run: async ({ args }) => {
@@ -31,13 +31,24 @@ export default defineCommand({
         const { getProjectDataDir } = await import('../../store/persistence.js');
         const { startDashboard } = await import('../../dashboard/server.js');
 
+        // The [server].dashboardPort config is a real default source; the
+        // explicit --port flag always wins.
+        let configuredDashboardPort: number | undefined;
+        try {
+            const { getServerConfig } = await import('../../config.js');
+            const serverConfig = getServerConfig();
+            configuredDashboardPort = typeof serverConfig.dashboardPort === 'number'
+                ? serverConfig.dashboardPort
+                : undefined;
+        } catch { /* config files are optional */ }
+
         const project = detectProject();
         if (!project) {
             console.error('Memorix requires a git repo to establish project identity. Run `git init` in this workspace first.');
             process.exit(1);
         }
         const dataDir = await getProjectDataDir(project.id);
-        const port = parseTcpPortOrReport(args.port as string | undefined, 3210);
+        const port = parseTcpPortOrReport(args.port as string | undefined, configuredDashboardPort ?? 3210);
         if (port === undefined) {
             process.exitCode = 1;
             return;