Search Memory
- 691 installs
- 148 repo stars
- Updated August 3, 2026
- nowledge-co/community
search-memory is an agent skill that retrieves relevant past decisions, solutions, and context from a personal knowledge base during agent conversations.
About
search-memory is an agent skill from nowledge-co/community that instructs coding agents to query a personal memory store when past insights would improve the current response. Instead of waiting for explicit recall requests, the skill defines autonomous recognition signals: continuity with prior work, pattern matches to solved problems, decision-context phrases like why we chose X, recurring themes, and implicit references such as that approach or like before. Developers reach for search-memory when agents should proactively surface documented breakthroughs, architecture rationale, and debugging root causes across sessions. The skill fits long-running projects where context drift causes repeated mistakes without memory retrieval.
- Proactively searches personal knowledge base when past insights would improve response quality
- Recognizes implicit recall language such as "that approach", "like before", or "the pattern we used"
- Routes between durable memory (`nmem --json m search`) and thread history (`nmem --json t search`)
- Triggers on references to previous work, named features, bugs, refactors, or recurring workflows
- Reduces redundant explanations and prevents repeating previously rejected solutions
Search Memory by the numbers
- 691 all-time installs (skills.sh)
- +17 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #612 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/nowledge-co/community --skill search-memoryAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 691 |
|---|---|
| repo stars | ★ 148 |
| Security audit | 3 / 3 scanners passed |
| Last updated | August 3, 2026 |
| Repository | nowledge-co/community ↗ |
How do agents retrieve past decisions from memory?
Retrieve relevant past decisions, solutions, and context from their personal knowledge base during agent conversations.
Who is it for?
Developers running long-lived agent sessions who store breakthroughs and decisions in a personal knowledge base and need proactive recall.
Skip if: One-off tasks with no persistent memory store or projects where every answer should come only from the current repository files.
When should I use this skill?
The conversation shows continuity with prior work, pattern matches to past issues, or implicit references to earlier decisions and solutions.
What you get
Relevant past decisions, documented solutions, architecture rationale, and session context injected into the agent response.
- Retrieved memory context
- Past decision summaries
- Relevant solution references
Files
Search Memory
When to Search (Autonomous Recognition)
Strong signals:
- Continuity: Current topic connects to prior work
- Pattern match: Problem resembles past solved issue
- Decision context: "Why/how we chose X" implies documented rationale
- Recurring theme: Topic discussed in past sessions
- Implicit recall: "that approach", "like before"
Contextual signals:
- Complex debugging (may match past root causes)
- Architecture discussion (choices may be documented)
- Domain-specific question (conventions likely stored)
Skip when:
- Fundamentally new topic
- Generic syntax questions
- Fresh perspective explicitly requested
Tool Usage
Use nmem CLI with --json flag for programmatic search:
# Basic search
nmem --json m search "3-7 core concepts"
# With filters
nmem --json m search "API design" --importance 0.8
# With labels (multiple labels use AND logic)
nmem --json m search "authentication" -l backend -l security
# With time filter
nmem --json m search "meeting notes" -t weekIf the runtime already knows the active project or agent lane, add --space "<space name>".
Query: Extract semantic core, preserve terminology, multi-language aware
Filters:
--importance MIN: Minimum importance score (0.0-1.0)-l, --label LABEL: Filter by label (can specify multiple)-t, --time RANGE: Time filter (today, week, month, year)-n NUM: Limit number of results (default: 10)
JSON Response: Parse memories array, check score field for relevance
Use thread search when the user is really asking about a prior conversation, previous session, or exact discussion:
nmem --json t search "query" --limit 5If a memory result includes source_thread or thread search finds the likely conversation, inspect it progressively instead of loading the whole thread at once:
nmem --json t show <thread_id> --limit 8 --offset 0 --content-limit 1200Increase --offset only when more messages are actually needed.
Scores: 0.6-1.0 direct | 0.3-0.6 related | <0.3 skip
Examples:
# Search with importance filter
nmem --json m search "database optimization" --importance 0.7
# Search with multiple labels
nmem --json m search "React patterns" -l frontend -l react
# Search recent memories
nmem --json m search "bug fix" -t week -n 5Response
Found: Synthesize, cite when helpful None: State clearly, suggest distilling if current discussion valuable
Troubleshooting
If nmem is not in PATH: pip install nmem-cli, or on Arch Linux yay -S nmem-cli / paru -S nmem-cli
For remote servers: run nmem config client set url https://... and nmem config client set api-key ... once on this machine.
Run /status to check server connection.
Related skills
Grill MeHave an agent relentlessly pressure-test their plan or design until every decision branch is resolved and shared understanding is reached.691k196kGrill With DocsPressure-test architecture decisions against their live codebase and living documentation before writing production code.585k196k
Lark CalendarLet their coding agents read, create, and manage events inside Lark (Feishu) Calendar directly from natural language instructions.493kLark ImLet their coding agent send instant notifications, post updates, and receive commands directly inside Lark (Feishu) workspaces.493kLark ContactLet their AI coding agents read and write contacts, send messages, and manage user data inside Lark (Feishu).493kLark AttendanceAutomatically fetch and report daily attendance data from Lark (Feishu) into their own tools or agents.493kFAQ
When does search-memory trigger automatically?
search-memory triggers when agents detect continuity with prior work, pattern matches to solved problems, decision-context phrases, recurring themes, or implicit recall like that approach. Complex debugging sessions also signal a memory search for past root causes.
What does search-memory retrieve?
search-memory retrieves relevant past decisions, documented solutions, breakthroughs, and architecture rationale from a personal knowledge base. The nowledge-co skill improves agent responses by injecting stored context without explicit user recall requests.
Is Search Memory safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.