Repository
rohitg00/agentmemory agent skills
- skills
- 17
- GitHub stars
- 29k
GitHub description: “#1 Persistent memory for AI coding agents based on real-world benchmarks”
- Stars
- 29,222 (2,556 forks)
- Licence
- Apache-2.0
- Last push
- Oct 2026
- Created
- Feb 2026
- Homepage
- agent-memory.dev
- agentmemory
- agents
- ai
- claude
- claudecode
- codex
- copilot
- cursor
- genai
- harness
- hermes
- memory
- openclaw
Install all skills
npx skills add rohitg00/agentmemoryAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in rohitg00/agentmemory, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Sets up and troubleshoots a local agentmemory install, covering the MCP connection, environment variables, ports, authentication and optional feature flags. | rohitg00/ | 29k | — | ~1k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 2 | Traces a file, function or line back to the agent session behind its current commit, using git blame and a memory lookup, and reports only what the records show. | rohitg00/ | 29k | — | ~522 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 3 | Lists recent git commits linked to agent sessions, filterable by branch, repository or a result limit, showing the session id and observation count behind each one. | rohitg00/ | 29k | — | ~524 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 4 | Deletes chosen memories from agentmemory only after showing the matches and getting an explicit yes, for privacy requests and cleanup of outdated notes. | rohitg00/ | 29k | — | ~612 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 5 | Resumes the most recent agent session for the current directory, leading with any question left unanswered and ending with a concrete next step. | rohitg00/ | 29k | — | ~678 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 6 | Distills a user correction or hard-won rule into a confidence-weighted lesson that resurfaces automatically before similar future work. | rohitg00/ | 29k | — | ~721 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 7 | Makes persistent agent memory pay off by searching before work starts and saving each decision the moment it settles, rather than batching a summary at the end. | rohitg00/ | 29k | — | ~831 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 8 | Searches agentmemory for past observations, sessions and learnings with hybrid keyword, vector and graph search, and reports only what comes back. | rohitg00/ | 29k | — | ~557 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 9 | Summarizes recent agent sessions for the current project by date, with each session's title, status, observation count and top highlights from memory. | rohitg00/ | 29k | — | ~510 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 10 | Saves an insight, decision or fact to agentmemory with specific concept tags and file paths, so a later recall can find it in a future session. | rohitg00/ | 29k | — | ~600 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 11 | Shows a clean, reverse-chronological timeline of recent sessions on a project, using only the data a memory tool actually returned, never a remembered summary. | rohitg00/ | 29k | — | ~465 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 12 | Sets the house format for writing or restructuring an agentmemory skill: a tiered SKILL.md under 100 lines, generated reference facts and a fixed style and checklist. | rohitg00/ | 29k | — | ~567 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 13 | Explains how the agentmemory connect command wires the memory server into host coding agents, and how to fix an adapter that writes the wrong config path. | rohitg00/ | 29k | — | ~402 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 14 | Describes the lifecycle hooks in the agentmemory Claude Code plugin that record observations automatically, and what to check when observations go missing. | rohitg00/ | 29k | — | ~444 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 15 | Covers the HTTP REST endpoints of the agentmemory server, its primary interface, for hosts without MCP or when MCP is unavailable. | rohitg00/ | 29k | — | ~404 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 16 | Explains how agentmemory is built: the iii engine it runs on, hybrid retrieval, the storage lifecycle, port layout and the web viewer. | rohitg00/ | 29k | — | ~476 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 17 | Indexes agentmemory's MCP tools by purpose, with a save-then-recall quick start and a reference file listing exact parameters. | rohitg00/ | 29k | — | ~545 | Automated safety check: Pass | Apache-2.0 | yesterday |
Questions, answered from the data.
What is the best skill in rohitg00/agentmemory?
agentmemory Setup and Diagnostics from rohitg00/agentmemory ranks first of the 17 skills in rohitg00/agentmemory listed here, with the highest score: its repository has 29k GitHub stars, its SKILL.md loads about 1k tokens and it has informational notes only in the automated safety check. Next come Commit Context Lookup and Agent Commit History.
Are the skills in rohitg00/agentmemory official?
None yet. All 17 skills in rohitg00/agentmemory listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from rohitg00/agentmemory?
Run npx skills add rohitg00/agentmemory in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.