DeepChat is an open-source desktop client for AI agents that keeps user data local first and connects agents with services such as MCP, Skills, ACP, and messaging apps. It is for people who want to use and control AI assistants from a desktop application. The catalogue add-ons extend DeepChat’s agent workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ThinkInAIXYZ/deepchat --skill nowledge-memgit clone --depth 1 https://github.com/ThinkInAIXYZ/deepchatWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/thinkinaixyz/deepchat/nowledge-mem)<a href="https://agentmods.dev/skills/thinkinaixyz/deepchat/nowledge-mem"><img src="https://agentmods.dev/badge/skills/thinkinaixyz/deepchat/nowledge-mem/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thinkinaixyz/deepchat/nowledge-mem"><img src="https://agentmods.dev/badge/skills/thinkinaixyz/deepchat/nowledge-mem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.00429 |
| Opus 5.5 | $0.00018 | $0.00172 |
| Sonnet 5.5 | $0.00009 | $0.00086 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
nowledge-mem scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Nowledge Mem
Use the enabled nowledge-mem-connection MCP tools for the server configured in Plugins >
Nowledge Mem. Keep that destination, returned identity and Space for the whole operation. Never mix results from
different Mem servers or silently retry on another server.
At the beginning of related work, read Context Bundle once (read_context_bundle, source_app
deepchat) for identity, scope, rules and Working Memory. Use read_working_memory only when the
bundle tool is unavailable. An empty Working Memory is a successful empty result.
For continuation, reviews, regressions and prior decisions, search memory_search with a narrow
query and limit 5, then fetch the relevant exact IDs. Search before adding a duplicate. Distinguish
recorded facts from proposals, and keep scope returned by the server. A graph is optional; only
show one when it enforces the same identity and Space as retrieval.
Save a concise durable learning with memory_add or update an existing memory only when it is
useful beyond this conversation. State what was saved. Do not save speculative conclusions as
facts. Save complete conversations only when the user requests it: use DeepChat's conversation
export to Nowledge Mem, which uses the same verified connection as MCP. Do not
claim an export happened without a successful acknowledgement.
For configuration or failed access, direct the user to Plugins > Nowledge Mem. The host verifies
REST and MCP and stores credentials securely. Report the failing connection and operation; do not
switch to localhost after a remote error. Do not ask for keys in chat, invoke unscoped nmem, edit
~/.nowledge-mem/config.json, read local Mem database files, or install another connector. This
plugin uses DeepChat's HTTP client and does not require the CLI.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 23d ago First seen · 32 lines · 45 tokens per session scan A 115a871d261c
nowledge-mem is a skill published in the GitHub repository ThinkInAIXYZ/deepchat (6,361 stars, last pushed 3d ago), licensed Apache-2.0. It adds 45 tokens to every session and 429 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.
Other skills, from other repositories
proactive-agent
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞.
memory-recall
Persistent cross-session memory system with fact extraction, semantic search, and compiled memory layers. Your agent remembers everything across sessions — user preferences, project context, past decisions, personal details. Use when: (1) User references something from a previous conversation, (2) Agent needs project…
purmemo
Persistent AI conversation memory. Recall context at session start, save progress at session end. Essential for project continuity across sessions.
honcho
Configure and troubleshoot Honcho memory for Hermes.
mem0-cli
Mem0 CLI -- the command-line interface for mem0 memory operations. TRIGGER when: user mentions "mem0 cli", "mem0 command line", "@mem0/cli", "mem0-cli", "pip install mem0-cli", "npm install -g @mem0/cli", or is running mem0 commands in a terminal/shell (mem0 add, mem0 search, mem0 list, mem0 get, mem0 init, mem0…
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…