"deepseek" matching MCP servers:

Enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine, allowing Claude to tackle complex multi-step reasoning tasks with greater precision.

Search local AI-agent conversation history by file or exact phrase, and recall original source turns. Four read-only stdio tools for Claude Code, Codex, DeepSeek Harness, Pi and ThoughtDAG history; source sessions are never modified.

Provides local-first project memory and compact engineering context for Codex and DeepSeek Harness, enabling agents to persist and retrieve project-scoped decisions, task checkpoints, and deterministic EIR/1 engineering facts across sessions.

Evidence-governed coding agent memory and knowledge lifecycle MCP server for DeepSeek Harness (DSH), OpenAI Codex, and Google Antigravity. Provides local SQLite FTS5 + semantic hybrid retrieval, automatic session/compaction checkpointing, counter-example demotion, and a hard 1,200-char context budget guardrail with zero third-party Python dependencies.

Gives DeepSeek Harness sessions persistent memory that survives restarts, exposing 52 tools for writing, recalling, compressing, and graphing memories alongside session summarization and code-change archaeology. Enables users to retain facts and context in an isolated personal namespace so later sessions can recall them automatically within a token budget.

Provides persistent OKF memory for DeepSeek Harness by storing and indexing Markdown memories in SQLite FTS5, enabling agents to search, store, and export memories through MCP tools.

Bridges TiMEM's cloud MCP server with DeepSeek Harness to provide long-term memory tools and automatic memory skills for AI models, enabling persistent context and learned behaviors across conversations.

Enables DeepSeek Harness agents to access DeepBrain's judgment store, including quoting verified lines, retrieving historical positions, and reusing analysis methods.

A remote MCP server that lets Claude call ChatGPT, DeepSeek, Kimi, and Gemini in one persistent shared discussion via a single ask_model tool, with transcript persistence and bearer authentication.

Enables Codex and DeepSeek Harness to maintain a local, traceable record of current task intent, separating requirements, evidence, unknowns, and disagreements while preserving corrections without erasing history.

Enables DeepSeek Harness agents to run bounded autonomous learning rounds that build a traceable, searchable knowledge base with evidence-based verification, conflict detection, and evaluation reports. High-risk actions such as code execution and knowledge updates are gated behind native host approval dialogs, with run mode, data directory, and daily budget configurable from a settings card.

Exposes a layered long-term memory store — persistent self blocks, four-tier scoped retrieval, knowledge graph, and signed knowledge capsules — over stdio so any MCP-capable client can use the same 15 memory tools and shared ACL. It lets Claude Desktop, IDE agents, and custom orchestrators mount that store without depending on the DeepSeek Harness runtime.

MCP server for verifying narrative consistency and querying story-state facts in DeepSeek Harness, exposing read-only ledger tools for canonical evidence and continuity checks.

Exposes DeepSeek Harness capabilities—durable memory, task ledger, project-agent dispatch, and the wider MCP estate—as declared MCP tools for any MCP client.

Enables DeepSeek Harness to use OpenViking persistent memory by recalling relevant context into conversations, mirroring sessions, committing at thresholds, replaying offline writes, and exposing OpenViking tools via MCP while guarding viking:// URIs.

Enables DeepSeek Harness to store conversation memories and perform semantic or hybrid memory retrieval through MemAura's cloud API, so agents can recall relevant context across sessions.

MCP server for querying a personal knowledge base using semantic RAG, powered by DeepSeek and local embeddings from Ollama.

Universal Git-powered persistent memory, context rules & native MCP server for AI coding agents. Prevents context amnesia with stateful workflows, Git Notes, and cross-model review gates across Claude, OpenAI, Gemini & DeepSeek in Cursor, Claude Code & VS Code.

Adds a local-first memory MCP server: long-term memory is stored as plain Markdown/JSONL files in a user-chosen directory (MEMORY_DIR) and can be shared by multiple MCP clients (Cherry Studio, Claude Desktop, DeepSeek Harness). * No database, no vector store, no network calls * Four tools: memory_read / memory_update / memory_append / memory_search * Shrink-protection + backup before overwrite *